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

    Neuronpedia

    INDEX
    Explanations

    improvement or effect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nam
    -0.07
     göster
    -0.06
     Devlet
    -0.06
     immensely
    -0.06
     newest
    -0.06
    机构
    -0.06
     Tuy
    -0.06
     Santos
    -0.06
    .exam
    -0.06
     честь
    -0.06
    POSITIVE LOGITS
    _git
    0.07
    _pitch
    0.07
    orů
    0.06
     unzip
    0.06
     dist
    0.06
     zx
    0.06
    739
    0.06
    _mB
    0.06
    ,request
    0.06
     SAL
    0.06
    Act Density 0.138%

    No Known Activations