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

    Neuronpedia

    INDEX
    Explanations

    references to progress or movement through situations or challenges

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

    work with directional prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.51
     lenker
    -0.50
    adaptiveStyles
    -0.47
    oredCriteria
    -0.46
    tanque
    -0.46
    Brainz
    -0.44
    ]")]
    -0.42
    Portail
    -0.42
     kebersihan
    -0.41
     wijze
    -0.41
    POSITIVE LOGITS
     working
    0.80
    Working
    0.77
    working
    0.75
     Worked
    0.71
     worked
    0.71
     Working
    0.70
    Worked
    0.66
     trabajar
    0.66
     WORKING
    0.65
    Trabaj
    0.63
    Act Density 0.010%

    No Known Activations