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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grace
    -0.08
     bud
    -0.07
     정
    -0.07
    .uc
    -0.07
    dept
    -0.07
    َم
    -0.07
     Carm
    -0.06
     طل
    -0.06
    spotify
    -0.06
    紹介
    -0.06
    POSITIVE LOGITS
    ACHE
    0.06
    chlor
    0.06
     revisions
    0.06
     Copper
    0.06
     floatValue
    0.06
    шиб
    0.06
    ії
    0.06
    UB
    0.06
     ambiguous
    0.06
     développement
    0.06
    Act Density 0.015%

    No Known Activations