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

    Neuronpedia

    INDEX
    Explanations

    hemisphere

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鉄道
    -0.07
    .binding
    -0.07
    placed
    -0.07
     напрям
    -0.06
     dry
    -0.06
    strained
    -0.06
    ۸
    -0.06
     primary
    -0.06
     문자
    -0.06
     ago
    -0.06
    POSITIVE LOGITS
     hemisphere
    0.13
     Hemisphere
    0.12
    _PROM
    0.07
     shim
    0.06
     decreasing
    0.06
    ากร
    0.06
    luğ
    0.06
     sharper
    0.06
    leme
    0.06
    shaft
    0.06
    Act Density 0.001%

    No Known Activations