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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     цар
    -0.06
     jedna
    -0.06
     dict
    -0.06
     This
    -0.06
    ikt
    -0.06
    pees
    -0.06
     один
    -0.06
     threatened
    -0.06
    něn
    -0.06
    (li
    -0.06
    POSITIVE LOGITS
    /browse
    0.07
    練
    0.07
    -popup
    0.06
    .Infof
    0.06
    .WindowManager
    0.06
    .pix
    0.06
     LATIN
    0.06
     censor
    0.06
     �
    0.06
     Прод
    0.06
    Act Density 0.057%

    No Known Activations