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

    Neuronpedia

    INDEX
    Explanations

    myths and legends

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ту
    -0.08
    \param
    -0.08
     يعد
    -0.08
     такое
    -0.08
    漤
    -0.07
     poner
    -0.07
    /rem
    -0.07
    .SetValue
    -0.07
    ']]['
    -0.07
    /title
    -0.07
    POSITIVE LOGITS
    ilib
    0.07
    变革
    0.07
     Cave
    0.07
     Gloria
    0.07
     Helm
    0.07
    implicit
    0.07
    istic
    0.07
    hill
    0.06
    克
    0.06
     beta
    0.06
    Act Density 0.101%

    No Known Activations