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

    Neuronpedia

    INDEX
    Explanations

    services and activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HM
    -0.08
     Rox
    -0.07
     Guerrero
    -0.07
    取り
    -0.07
    ниця
    -0.07
     мер
    -0.06
     journalism
    -0.06
     therm
    -0.06
     vandal
    -0.06
     Gamer
    -0.06
    POSITIVE LOGITS
     '\''
    0.06
     kní
    0.06
    释
    0.06
    lica
    0.06
    aily
    0.06
    .uml
    0.06
    �
    0.06
    .descriptor
    0.06
    OVÁ
    0.06
     сах
    0.06
    Act Density 0.070%

    No Known Activations