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

    Neuronpedia

    INDEX
    Explanations

    Fenwick Tree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rejected
    -0.08
     night
    -0.08
    _episode
    -0.08
    Night
    -0.08
    _alarm
    -0.08
     rejected
    -0.08
     claras
    -0.07
    Match
    -0.07
     depres
    -0.07
     unreal
    -0.07
    POSITIVE LOGITS
    -ს
    0.10
    Fen
    0.10
     дошта
    0.10
     జిల్ల
    0.09
     ജില്ല
    0.09
     aamma
    0.09
    .linear
    0.09
     მაინ
    0.09
     დიზ
    0.09
     սն
    0.09
    Act Density 0.002%

    No Known Activations