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

    Neuronpedia

    INDEX
    Explanations

    Statistics and numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    legal
    -0.07
     struggles
    -0.07
     chilled
    -0.06
     cause
    -0.06
    动作
    -0.06
     meinen
    -0.06
     �
    -0.06
    _GAIN
    -0.06
     спе
    -0.06
    准
    -0.06
    POSITIVE LOGITS
    oid
    0.07
     وبالتالي
    0.07
    (contact
    0.06
    MODE
    0.06
    _inode
    0.06
     RESOURCE
    0.06
     Mo
    0.06
    폰
    0.06
    ✉
    0.06
     bisexual
    0.06
    Act Density 0.119%

    No Known Activations