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

    Neuronpedia

    INDEX
    Explanations

    call followed by someone or for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lobkovic
    0.74
     Geschwindigkeit
    0.71
    謾
    0.66
     கொள்ளுங்கள்
    0.66
     gills
    0.64
     Investig
    0.64
    <0x9B>
    0.63
     immensely
    0.63
     añadido
    0.63
     গাড়
    0.63
    POSITIVE LOGITS
    Call
    1.08
    call
    1.06
    1
    1.02
     call
    0.99
    కు
    0.97
    Calling
    0.87
    8
    0.85
    は
    0.82
    지
    0.80
    呼
    0.80
    Act Density 0.038%

    No Known Activations