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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal protections and their implications

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

    purpose or intent behind actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.88
    DockStyle
    -0.72
     Administrativna
    -0.69
     Biôgrafia
    -0.68
    ftagPool
    -0.68
    balleur
    -0.67
     initComponents
    -0.66
    SourceChecksum
    -0.65
    .*")]
    -0.64
     تضيفلها
    -0.63
    POSITIVE LOGITS
     economic
    0.35
    ordning
    0.31
     aims
    0.31
     designed
    0.31
     dorada
    0.31
    —
    0.31
     built
    0.30
     protectora
    0.30
     aimed
    0.29
     protect
    0.29
    Act Density 0.100%

    No Known Activations