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

    Neuronpedia

    INDEX
    Explanations

    above

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    
    -0.07
    *self
    -0.06
     browse
    -0.06
    *y
    -0.06
    .dropout
    -0.06
    派
    -0.06
     میدان
    -0.06
     BaseController
    -0.06
     puta
    -0.06
     Laf
    -0.06
    POSITIVE LOGITS
    asurer
    0.07
     transient
    0.06
     venue
    0.06
     concise
    0.06
    girl
    0.06
    Spinner
    0.06
    ///<
    0.06
     )
    0.06
    .training
    0.06
     trem
    0.06
    Act Density 0.068%

    No Known Activations