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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fw
    -0.07
     blonde
    -0.07
     showcases
    -0.07
    INGTON
    -0.07
     Page
    -0.07
     competence
    -0.07
     informat
    -0.07
     bande
    -0.07
    不克不及
    -0.07
     Vermont
    -0.07
    POSITIVE LOGITS
     işlem
    0.08
    ió
    0.08
     lose
    0.07
    اعة
    0.07
    𝔷
    0.07
    ካ
    0.07
    עו
    0.07
    𬴃
    0.07
    亏
    0.07
     dik
    0.07
    Act Density 0.002%

    No Known Activations