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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dependencies
    -0.07
    ائلة
    -0.07
     봐
    -0.07
    Release
    -0.07
     detailed
    -0.07
    IntPtr
    -0.06
    psilon
    -0.06
    IFIED
    -0.06
    (instance
    -0.06
    cheon
    -0.06
    POSITIVE LOGITS
     ents
    0.06
    .onPause
    0.06
     Каб
    0.06
    наче
    0.06
     RSVP
    0.06
    hold
    0.06
    .filename
    0.06
    .detach
    0.06
    グル
    0.06
    PLUGIN
    0.06
    Act Density 0.002%

    No Known Activations