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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    415
    -0.07
    ortality
    -0.07
     Ali
    -0.06
     menn
    -0.06
    _SETTINGS
    -0.06
    されて
    -0.06
    結婚
    -0.06
    Contacts
    -0.06
    ImageRelation
    -0.06
    erosis
    -0.06
    POSITIVE LOGITS
     síd
    0.07
     안전
    0.07
    ]=[
    0.07
    _crossentropy
    0.07
     надо
    0.07
    -available
    0.06
     خم
    0.06
     �
    0.06
     advancing
    0.06
     Dummy
    0.06
    Act Density 0.042%

    No Known Activations