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

    Neuronpedia

    INDEX
    Explanations

    signal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    over
    -0.07
    .getBy
    -0.07
     head
    -0.06
    обав
    -0.06
     atroc
    -0.06
    Hour
    -0.06
    kle
    -0.06
    .restore
    -0.06
    /etc
    -0.06
     вра
    -0.06
    POSITIVE LOGITS
     Advisors
    0.07
    แนะ
    0.07
    602
    0.06
    �
    0.06
     Educational
    0.06
     occupational
    0.06
    Tube
    0.06
    procs
    0.06
     methodologies
    0.06
     Arts
    0.06
    Act Density 0.000%

    No Known Activations