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

    Neuronpedia

    INDEX
    Explanations

    Electronics and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vals
    -0.07
     $
    -0.07
    Mit
    -0.07
     helmets
    -0.06
     nossa
    -0.06
    gh
    -0.06
    ák
    -0.06
    �
    -0.06
     PW
    -0.06
     renewed
    -0.06
    POSITIVE LOGITS
     /////
    0.07
     strtol
    0.06
    izzling
    0.06
     SEX
    0.06
     Galaxy
    0.06
     ANT
    0.06
    ApplicationBuilder
    0.06
    .getLogin
    0.06
     Excell
    0.06
    .heading
    0.06
    Act Density 0.013%

    No Known Activations