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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    statements
    -0.07
     escalated
    -0.06
    initialized
    -0.06
     �
    -0.06
     сест
    -0.06
     early
    -0.06
     accusation
    -0.06
    StackTrace
    -0.06
    payload
    -0.06
     واس
    -0.06
    POSITIVE LOGITS
     TInt
    0.07
     bếp
    0.07
    .navigationItem
    0.07
     Ventura
    0.07
    .BooleanField
    0.07
    .sy
    0.07
    =str
    0.06
    テレビ
    0.06
    clidean
    0.06
     Randall
    0.06
    Act Density 0.145%

    No Known Activations