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

    Neuronpedia

    INDEX
    Explanations

    -x

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     provocative
    -0.07
    abolic
    -0.07
    绛
    -0.07
    瘅
    -0.07
     surreal
    -0.06
    �
    -0.06
    ⓔ
    -0.06
    情报
    -0.06
    推介
    -0.06
    FromString
    -0.06
    POSITIVE LOGITS
    experience
    0.07
     FX
    0.07
     clin
    0.07
    eut
    0.07
    omega
    0.07
     dealing
    0.07
     organiz
    0.07
    pi
    0.07
    作为
    0.07
    allo
    0.06
    Act Density 0.001%

    No Known Activations