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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ist
    -0.06
    пос
    -0.06
     recycl
    -0.06
     پش
    -0.06
     compromising
    -0.06
     bumper
    -0.06
    历
    -0.06
     kuv
    -0.06
    Track
    -0.06
    Trigger
    -0.06
    POSITIVE LOGITS
    rette
    0.07
    Object
    0.06
    .osgi
    0.06
     lavoro
    0.06
     case
    0.06
    _PROFILE
    0.06
    ceil
    0.06
    ANO
    0.06
     muse
    0.06
     iterative
    0.06
    Act Density 0.080%

    No Known Activations