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

    Neuronpedia

    INDEX
    Explanations

    except, than

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ж
    -0.08
    .SDK
    -0.08
     newY
    -0.08
    Signing
    -0.07
    ᠨ
    -0.07
     traged
    -0.07
    (LOG
    -0.07
     DEST
    -0.07
     minY
    -0.07
     XIII
    -0.07
    POSITIVE LOGITS
    멭
    0.07
    strained
    0.07
    טענות
    0.07
    互通
    0.07
    chn
    0.07
    Struct
    0.07
    ры
    0.06
    isman
    0.06
    .metadata
    0.06
    0.06
    Act Density 0.023%

    No Known Activations