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

    Neuronpedia

    INDEX
    Explanations

    iOS/Android programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SEMB
    -0.08
    �
    -0.07
    Disposition
    -0.07
    inburgh
    -0.07
    _increment
    -0.07
     προς
    -0.07
    ב
    -0.07
    CRET
    -0.07
     punished
    -0.06
     Twilight
    -0.06
    POSITIVE LOGITS
     �
    0.07
    (named
    0.07
     определить
    0.07
     사망
    0.06
    izedName
    0.06
     indian
    0.06
     провести
    0.06
    layer
    0.06
     فتح
    0.06
    anch
    0.06
    Act Density 0.002%

    No Known Activations