Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to permissions and approvals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by prepositions, particularly "of" and "from"

    np_acts-logits-general · gemini-2.0-flash

    approval, permission, consent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lenker
    -0.71
    Autoritní
    -0.62
    hatt
    -0.56
    StateToProps
    -0.53
     /\.
    -0.51
     Paix
    -0.51
     doth
    -0.50
    +:+
    -0.49
     MessageBoxIcon
    -0.49
    erus
    -0.48
    POSITIVE LOGITS
     received
    0.85
    received
    0.76
     from
    0.76
     reç
    0.74
     Received
    0.66
     recib
    0.66
     recieved
    0.63
     recibido
    0.62
     받
    0.62
     mergeFrom
    0.61
    Act Density 0.464%

    No Known Activations