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

    Neuronpedia

    INDEX
    Explanations

    data analysis and collection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.56
     send
    0.56
    ون
    0.54
     h
    0.53
     l
    0.53
    ：
    0.53
     en
    0.51
    le
    0.50
     medicine
    0.49
     I
    0.49
    POSITIVE LOGITS
     شہریوں
    0.54
    पुढे
    0.51
    जानिए
    0.49
    Ahora
    0.49
    N
    0.49
    embryon
    0.48
    साठी
    0.48
    好吃
    0.48
    Estamos
    0.48
    Vor
    0.48
    Act Density 0.010%

    No Known Activations