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

    Neuronpedia

    INDEX
    Explanations

    DOB

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     veto
    -0.08
     killers
    -0.07
    EPHIR
    -0.07
    ERICA
    -0.07
     unnamed
    -0.07
     Fak
    -0.07
     seas
    -0.06
    read
    -0.06
     Helsinki
    -0.06
    intern
    -0.06
    POSITIVE LOGITS
    Ό
    0.07
    ับท
    0.07
    Optional
    0.06
    わたし
    0.06
    “I
    0.06
    (fb
    0.06
    PathVariable
    0.06
     curb
    0.06
    śli
    0.06
     skillet
    0.06
    Act Density 0.005%

    No Known Activations