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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -room
    -0.07
     مهر
    -0.07
     صنعت
    -0.06
    цер
    -0.06
     Woo
    -0.06
     steal
    -0.06
    _fence
    -0.06
    .items
    -0.06
    ίου
    -0.06
     Cyr
    -0.06
    POSITIVE LOGITS
    �
    0.07
     rež
    0.07
    xed
    0.07
     yandan
    0.06
    Respond
    0.06
    [sub
    0.06
    egrated
    0.06
    (class
    0.06
    browse
    0.06
    ismatch
    0.06
    Act Density 0.000%

    No Known Activations