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

    Neuronpedia

    INDEX
    Explanations

    Kerala

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .asp
    -0.31
    楼ä¸ĭ
    -0.27
    undra
    -0.26
     caut
    -0.26
    grounds
    -0.26
    Ĭ¶
    -0.26
     downstairs
    -0.26
    该éĻ¢
    -0.25
    etheless
    -0.25
    king
    -0.25
    POSITIVE LOGITS
     enterprises
    0.24
    erman
    0.24
    ÙĦÙħ
    0.24
    achten
    0.23
    spath
    0.23
    abei
    0.23
    spirit
    0.23
     mean
    0.23
     Kun
    0.23
    ç©¿
    0.23
    Act Density 0.005%

    No Known Activations