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

    Neuronpedia

    INDEX
    Explanations

    phrases related to control or manipulation

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

    trust in his hands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.61
    __(/*!
    -0.56
     utafitiHapana
    -0.50
    Carriera
    -0.47
    verwijspagina
    -0.45
    RTDA
    -0.45
    fileID
    -0.45
     Signalez
    -0.44
    apiClient
    -0.44
    ſelves
    -0.44
    POSITIVE LOGITS
     handen
    0.48
     hands
    0.42
     руки
    0.40
     händer
    0.39
     manos
    0.37
     Händen
    0.37
     geha
    0.36
     mãos
    0.36
    værende
    0.36
     complètes
    0.35
    Act Density 0.071%

    No Known Activations