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

    Neuronpedia

    INDEX
    Explanations

    produced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     freezing
    -0.07
    relative
    -0.07
    Perfil
    -0.06
     Dry
    -0.06
     exclusive
    -0.06
    Preferences
    -0.06
     объем
    -0.06
     Helsinki
    -0.06
     loyal
    -0.06
     exclusively
    -0.06
    POSITIVE LOGITS
    ´
    0.06
    bookmark
    0.06
    enchmark
    0.06
    ebilirsiniz
    0.06
    "][$
    0.06
    '=>"
    0.06
    _PROTOCOL
    0.06
    瓦
    0.06
     milfs
    0.06
    �
    0.06
    Act Density 0.086%

    No Known Activations