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

    Neuronpedia

    INDEX
    Explanations

    mut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     باشد
    -0.07
     rif
    -0.07
     بیر
    -0.06
    illis
    -0.06
    BED
    -0.06
     blackout
    -0.06
    _layers
    -0.06
    outil
    -0.06
     aantal
    -0.06
    Prefab
    -0.06
    POSITIVE LOGITS
    mut
    0.08
     म
    0.06
     Γεν
    0.06
    	store
    0.06
     ],↵
    0.06
    653
    0.06
    -м
    0.06
     Movie
    0.06
     dreamed
    0.06
     NEW
    0.06
    Act Density 0.000%

    No Known Activations