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

    Neuronpedia

    INDEX
    Explanations

    statistical frequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fit
    -0.07
    "?>↵
    -0.06
     mutant
    -0.06
    }}},↵
    -0.06
    по
    -0.06
     Xavier
    -0.06
     warmed
    -0.06
     Cy
    -0.06
    flatMap
    -0.06
    .getState
    -0.06
    POSITIVE LOGITS
    tron
    0.08
    ENGINE
    0.08
     şirket
    0.07
     Rate
    0.07
     Explosion
    0.07
     hopping
    0.06
    _Function
    0.06
     Bloody
    0.06
     chests
    0.06
     Trash
    0.06
    Act Density 0.035%

    No Known Activations