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

    Neuronpedia

    INDEX
    Explanations

    Time until an event

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    άλυψης
    -0.07
    然后
    -0.06
     并
    -0.06
    JAVA
    -0.06
    mounted
    -0.06
     Saturn
    -0.06
     Defaults
    -0.06
    EqualTo
    -0.06
     bleed
    -0.06
     Больш
    -0.06
    POSITIVE LOGITS
    identity
    0.07
     tedav
    0.07
    يك
    0.06
    _modules
    0.06
     Pand
    0.06
    )(
    0.06
     uncomment
    0.06
    .REG
    0.06
     İmpar
    0.06
    _assert
    0.06
    Act Density 0.016%

    No Known Activations