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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .logical
    -0.08
     boiling
    -0.07
    ět
    -0.07
     bursting
    -0.06
     wasm
    -0.06
     forbidden
    -0.06
     Wasser
    -0.06
    �
    -0.06
     *
↵
    -0.06
     drums
    -0.06
    POSITIVE LOGITS
    ॉक
    0.08
     güvenilir
    0.07
    Shock
    0.07
    >}</
    0.06
    需求
    0.06
     homosexuals
    0.06
    СО
    0.06
    department
    0.06
    اس
    0.06
     underrated
    0.06
    Act Density 0.036%

    No Known Activations