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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cost
    -0.07
    Mounted
    -0.07
     barrier
    -0.07
     Await
    -0.06
     library
    -0.06
     change
    -0.06
    '";↵
    -0.06
    singleton
    -0.06
     habitat
    -0.06
    messages
    -0.06
    POSITIVE LOGITS
     Muhammed
    0.07
     �
    0.07
    earchBar
    0.06
    �
    0.06
     müzik
    0.06
    MG
    0.06
    edik
    0.06
    getti
    0.06
    etro
    0.06
    LETED
    0.06
    Act Density 0.105%

    No Known Activations