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

    Neuronpedia

    INDEX
    Explanations

    references to friendships and social interactions

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

    social relationships and family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DataPropertyName
    -0.35
     způso
    -0.33
     instantaneous
    -0.32
     Regel
    -0.31
     capture
    -0.30
     remp
    -0.30
     bride
    -0.30
    localVar
    -0.30
    ungsver
    -0.29
     model
    -0.29
    POSITIVE LOGITS
     zwiſchen
    0.55
    Попис
    0.54
    vician
    0.53
    Colleg
    0.53
     ddelweddau
    0.52
    bukkit
    0.51
    醐
    0.51
    __':
    0.50
    chyma
    0.48
    ReusableCell
    0.48
    Act Density 0.011%

    No Known Activations