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

    Neuronpedia

    INDEX
    Explanations

    Decrease or prevention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    düğ
    -0.06
    ethyst
    -0.06
     lup
    -0.06
    安
    -0.06
     lista
    -0.06
    ्रत
    -0.06
    ignet
    -0.06
    +".
    -0.06
     nur
    -0.06
     '</
    -0.06
    POSITIVE LOGITS
    _Game
    0.07
     باشید
    0.07
     diabetes
    0.07
     spectators
    0.07
     Executors
    0.07
     Asphalt
    0.07
     observational
    0.06
    _AFTER
    0.06
    amel
    0.06
    /tcp
    0.06
    Act Density 0.429%

    No Known Activations