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

    Neuronpedia

    INDEX
    Explanations

    domain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itä
    -0.06
     NORMAL
    -0.06
    _INC
    -0.06
    _site
    -0.06
     smiling
    -0.06
     +/-
    -0.06
    (targetEntity
    -0.05
    shima
    -0.05
     intro
    -0.05
    éf
    -0.05
    POSITIVE LOGITS
     biz
    0.07
    21
    0.07
    lahoma
    0.07
     Liber
    0.07
    /live
    0.06
    例
    0.06
     Stability
    0.06
     healthier
    0.06
    tlement
    0.06
    務
    0.06
    Act Density 0.003%

    No Known Activations