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

    Neuronpedia

    INDEX
    Explanations

    Ellipsis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ARRY
    -0.07
     Marriott
    -0.07
    _non
    -0.07
     Sty
    -0.07
     stray
    -0.07
    �
    -0.07
     dall
    -0.07
     Otto
    -0.07
    _RESP
    -0.07
     ptr
    -0.07
    POSITIVE LOGITS
    ã
    0.08
    でき
    0.07
    ेख
    0.07
    ..
    0.07
    wave
    0.07
    cm
    0.07
    握
    0.06
    俺は
    0.06
    ase
    0.06
    طاق
    0.06
    Act Density 0.016%

    No Known Activations