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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AuthToken
    -0.07
    (iter
    -0.07
    　　　 　 　 　
    -0.07
    573
    -0.07
    _ACTIVITY
    -0.06
     Published
    -0.06
     giống
    -0.06
    inst
    -0.06
    HTMLElement
    -0.06
    _Pro
    -0.06
    POSITIVE LOGITS
    (theta
    0.06
     atas
    0.06
     iconic
    0.06
     overhead
    0.06
    frac
    0.06
     grads
    0.06
    ivet
    0.05
     crochet
    0.05
     retrieval
    0.05
    alu
    0.05
    Act Density 0.113%

    No Known Activations