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

    Neuronpedia

    INDEX
    Explanations

    Cast

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STATE
    -0.07
    abbrev
    -0.07
     albums
    -0.07
    _FIRE
    -0.06
     appId
    -0.06
    	Rect
    -0.06
    ,"
    -0.06
    ahl
    -0.06
    observ
    -0.06
     opráv
    -0.06
    POSITIVE LOGITS
     Charlotte
    0.07
    _spaces
    0.06
     vrij
    0.06
     Ricardo
    0.06
    /support
    0.06
     Anti
    0.06
     comentarios
    0.06
     dalam
    0.06
    .project
    0.06
     beware
    0.06
    Act Density 0.006%

    No Known Activations