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

    Neuronpedia

    INDEX
    Explanations

    free

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    {};↵
    -0.07
     {};↵
    -0.07
     Xem
    -0.06
     {};↵↵
    -0.06
    AxisAlignment
    -0.06
    jeme
    -0.06
     уд
    -0.06
    arsed
    -0.06
     accompanied
    -0.06
     ří
    -0.06
    POSITIVE LOGITS
    ddl
    0.07
     glam
    0.07
     indemn
    0.06
     ',
    0.06
     extras
    0.06
    opath
    0.06
    olph
    0.06
    .Txt
    0.06
    minimal
    0.06
     disillusion
    0.06
    Act Density 0.005%

    No Known Activations