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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iena
    -0.08
    -rule
    -0.08
    Statements
    -0.08
    rens
    -0.08
     grads
    -0.07
    -document
    -0.07
    flush
    -0.07
    Regular
    -0.06
    MMM
    -0.06
    -test
    -0.06
    POSITIVE LOGITS
     UNU
    0.06
     ελλην
    0.06
    .&
    0.06
     غير
    0.06
     Tottenham
    0.06
    자료
    0.06
    Residents
    0.06
    .MON
    0.06
    potential
    0.06
     "_
    0.06
    Act Density 0.023%

    No Known Activations