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

    Neuronpedia

    INDEX
    Explanations

    act

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eerie
    -0.07
     �
    -0.07
    _CURSOR
    -0.06
    arius
    -0.06
    Multiplier
    -0.06
    осудар
    -0.06
     vyb
    -0.06
     طور
    -0.06
    iese
    -0.06
    žel
    -0.06
    POSITIVE LOGITS
     deduct
    0.07
     ทาง
    0.07
    ัต
    0.07
     retract
    0.07
    roach
    0.07
    action
    0.07
     Authors
    0.06
    (auth
    0.06
    das
    0.06
    νι
    0.06
    Act Density 0.002%

    No Known Activations