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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tractive
    -0.07
     Imm
    -0.06
     Uzbek
    -0.06
     初
    -0.06
    -0.06
    Coefficient
    -0.06
     majet
    -0.06
    拔
    -0.06
    �
    -0.06
    ToUpper
    -0.06
    POSITIVE LOGITS
    μι
    0.07
     manages
    0.07
     occurrences
    0.07
     rubber
    0.07
     baş
    0.07
    ),(
    0.07
    DER
    0.06
     пл
    0.06
    .update
    0.06
     adap
    0.06
    Act Density 0.145%

    No Known Activations