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

    Neuronpedia

    INDEX
    Explanations

    code syntax elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fruits
    -0.07
     allegation
    -0.06
    ulnerable
    -0.06
    ются
    -0.06
    (nombre
    -0.06
    ibration
    -0.06
    lığını
    -0.06
     можуть
    -0.06
     Reg
    -0.06
    unprocessable
    -0.06
    POSITIVE LOGITS
    (()=>{↵
    0.07
    枚
    0.06
    vr
    0.06
    .free
    0.06
     cn
    0.06
    五月
    0.06
     jack
    0.06
     Qualcomm
    0.06
     express
    0.06
     avantaj
    0.06
    Act Density 0.006%

    No Known Activations