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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to objects or entities

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

    it/them followed by prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     initComponents
    -0.43
    tinyos
    -0.39
     linkovi
    -0.38
     للاسماء
    -0.37
     Brust
    -0.36
     Marín
    -0.36
     больших
    -0.36
     cansado
    -0.35
     Sach
    -0.35
     disposição
    -0.35
    POSITIVE LOGITS
    MLLoader
    0.61
    LEncoder
    0.57
     EconPapers
    0.53
    dafx
    0.52
     Biôgrafia
    0.52
    BeginContext
    0.51
    eleste
    0.51
    ServletException
    0.49
    }{*}{
    0.48
    cerpt
    0.47
    Act Density 0.062%

    No Known Activations