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

    Neuronpedia

    INDEX
    Explanations

    solvable groups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ισχ
    -0.07
    ahu
    -0.07
     avalanche
    -0.07
    ριο
    -0.07
    aud
    -0.06
    [B
    -0.06
     �
    -0.06
    idis
    -0.06
    openid
    -0.06
     což
    -0.06
    POSITIVE LOGITS
    Foreground
    0.07
     sympathy
    0.07
    ugar
    0.07
     torrents
    0.06
     come
    0.06
     Drama
    0.06
    ١
    0.06
    �
    0.06
    	option
    0.06
     Krist
    0.06
    Act Density 0.004%

    No Known Activations