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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ailed
    -0.08
    Miss
    -0.08
     willingness
    -0.07
    spect
    -0.07
    ammed
    -0.07
     yardımc
    -0.07
     interactive
    -0.07
     parms
    -0.07
    人次
    -0.07
     time
    -0.07
    POSITIVE LOGITS
    蹶
    0.08
     BUT
    0.07
    jących
    0.07
    Actually
    0.07
    ทำความ
    0.07
    因為
    0.07
    .Block
    0.06
    _radio
    0.06
     صغ
    0.06
    ERRQ
    0.06
    Act Density 0.011%

    No Known Activations