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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MID
    -0.06
     Mid
    -0.06
    gres
    -0.06
    ětí
    -0.06
    259
    -0.06
    xis
    -0.06
     května
    -0.06
    ходит
    -0.06
    子は
    -0.06
    OCKET
    -0.06
    POSITIVE LOGITS
     RedirectTo
    0.07
    ↵↵↵↵↵↵
    0.07
    _$_
    0.07
    혹
    0.07
     ambiguous
    0.07
     nhiễm
    0.06
     brides
    0.06
    ↵↵↵↵↵↵↵↵
    0.06
     müşteri
    0.06
    _experience
    0.06
    Act Density 0.004%

    No Known Activations