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

    Neuronpedia

    INDEX
    Explanations

    true

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    deal
    -0.07
    issues
    -0.06
     division
    -0.06
    achs
    -0.06
    iotic
    -0.06
     Gap
    -0.06
    job
    -0.06
     belonging
    -0.06
    가격
    -0.06
    endency
    -0.06
    POSITIVE LOGITS
    .VISIBLE
    0.08
    (true
    0.08
     assertTrue
    0.08
    THR
    0.07
     True
    0.07
     Tre
    0.07
    .assertTrue
    0.07
    (True
    0.07
    ,true
    0.07
    _OK
    0.07
    Act Density 0.021%

    No Known Activations