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

    Neuronpedia

    INDEX
    Explanations

    long text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bel
    -0.06
    Isn
    -0.06
    partials
    -0.06
     große
    -0.06
    20
    -0.06
     blank
    -0.06
     bum
    -0.06
     pelic
    -0.06
    .Non
    -0.06
     bored
    -0.06
    POSITIVE LOGITS
    {})
    0.08
    /password
    0.07
    volt
    0.07
    /archive
    0.06
    [OF
    0.06
    enerator
    0.06
     �
    0.06
    عه
    0.06
    ighthouse
    0.06
    HttpPost
    0.06
    Act Density 0.040%

    No Known Activations