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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fuck
    -0.06
     Harry
    -0.06
    .Singleton
    -0.06
    ClassName
    -0.06
    avenport
    -0.06
    _pll
    -0.06
     spirited
    -0.05
     Schwarz
    -0.05
     самов
    -0.05
    Millis
    -0.05
    POSITIVE LOGITS
     Configuration
    0.07
    Crystal
    0.07
     Shotgun
    0.06
     drove
    0.06
    TR
    0.06
    ох
    0.06
     전화
    0.06
     lane
    0.06
    لان
    0.06
     Congo
    0.06
    Act Density 0.044%

    No Known Activations