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

    Neuronpedia

    INDEX
    Explanations

    highways

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    стру
    -0.07
     kan
    -0.07
     getColumn
    -0.07
     Moderator
    -0.07
     tumors
    -0.06
     wards
    -0.06
     rozvoj
    -0.06
    	buf
    -0.06
     bom
    -0.06
     Perform
    -0.06
    POSITIVE LOGITS
    _MACHINE
    0.07
    égor
    0.06
     hair
    0.06
    _DECREF
    0.06
    flatten
    0.06
    MMdd
    0.06
    atsby
    0.06
    řaz
    0.06
     світ
    0.06
    .MediaType
    0.06
    Act Density 0.007%

    No Known Activations