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

    Neuronpedia

    INDEX
    Explanations

    list formatting and bolding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ctomy
    0.71
     podpis
    0.70
    Смалянчук
    0.69
    しゃ
    0.69
    buildCommand
    0.68
     야
    0.67
    ާތ
    0.67
     arus
    0.66
     sewers
    0.66
     전류
    0.66
    POSITIVE LOGITS
     ---
    0.73
    ##
    0.72
    －－
    0.71
     ----------
    0.70
    ↵↵↵↵
    0.69
    ___
    0.69
    ---
    0.69
    ----------------
    0.69
    <0x96>
    0.69
    **
    0.68
    Act Density 0.684%

    No Known Activations