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

    Neuronpedia

    INDEX
    Explanations

    This

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HL
    -0.06
     obey
    -0.06
     ferr
    -0.06
     �
    -0.06
    bla
    -0.06
     libro
    -0.06
    tridges
    -0.06
    デル
    -0.06
     grid
    -0.06
    _PROM
    -0.05
    POSITIVE LOGITS
    MainThread
    0.07
    -campus
    0.07
    صب
    0.07
    žit
    0.06
    pipe
    0.06
    ，”
    0.06
     anders
    0.06
    (ns
    0.06
     alleen
    0.06
    ivé
    0.06
    Act Density 0.041%

    No Known Activations