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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fault
    -0.08
    ixe
    -0.07
    Purpose
    -0.07
     violent
    -0.06
    .rand
    -0.06
     palm
    -0.06
    �
    -0.06
    _precision
    -0.06
     sürdür
    -0.06
    毒
    -0.06
    POSITIVE LOGITS
    Boot
    0.07
    ूड
    0.06
    чий
    0.06
    _HE
    0.06
    :',
    0.06
    ervative
    0.06
    _RES
    0.06
     ("/
    0.06
     ReturnValue
    0.06
     새글
    0.06
    Act Density 0.052%

    No Known Activations