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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tro
    -0.06
    _ext
    -0.06
    にも
    -0.06
    _INET
    -0.06
    =s
    -0.06
    しない
    -0.06
    तर
    -0.06
    -0.06
    _THRESH
    -0.06
    (home
    -0.06
    POSITIVE LOGITS
    措
    0.07
     brake
    0.06
    loys
    0.06
    STA
    0.06
     stainless
    0.06
     आय
    0.06
     allowable
    0.06
     зміни
    0.06
     Syntax
    0.06
    σου
    0.06
    Act Density 0.051%

    No Known Activations