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

    Neuronpedia

    INDEX
    Explanations

    say the ending ') or ,'

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     apenas
    -0.06
    enticator
    -0.06
    within
    -0.06
    _plugin
    -0.06
    .red
    -0.06
    یط
    -0.06
    senha
    -0.06
    ()));↵↵
    -0.06
    _date
    -0.06
    ιστή
    -0.06
    POSITIVE LOGITS
     CUSTOM
    0.07
    ++↵
    0.07
     luật
    0.07
     *_
    0.07
    _WAIT
    0.07
     nuanced
    0.06
     enumer
    0.06
     comunic
    0.06
     Removal
    0.06
     LH
    0.06
    Act Density 0.006%

    No Known Activations