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

    Neuronpedia

    INDEX
    Explanations

    peremptory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nejen
    -0.07
    =%.
    -0.06
     správ
    -0.06
     pero
    -0.06
    _year
    -0.06
     týd
    -0.06
    _crypto
    -0.06
     alist
    -0.06
    Isl
    -0.06
     olduğunu
    -0.06
    POSITIVE LOGITS
    ротив
    0.07
     Right
    0.07
    atively
    0.06
    orent
    0.06
     hãng
    0.06
     후
    0.06
    ight
    0.06
     욕
    0.06
    _places
    0.06
    .Right
    0.06
    Act Density 0.000%

    No Known Activations