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

    Neuronpedia

    INDEX
    Explanations

    kind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coward
    -0.07
     nghiệ
    -0.06
    ư
    -0.06
    abilit
    -0.06
     louder
    -0.06
    _tele
    -0.06
     наруж
    -0.06
    �
    -0.06
    .beh
    -0.06
    cob
    -0.06
    POSITIVE LOGITS
     بشكل
    0.07
     activ
    0.06
     successes
    0.06
     Seeing
    0.06
    Cipher
    0.06
     baseman
    0.06
    ση
    0.06
     admiration
    0.06
    �ng
    0.06
     growers
    0.06
    Act Density 0.000%

    No Known Activations