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

    Neuronpedia

    INDEX
    Explanations

    leave at the door

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Harold
    -0.06
    "))↵↵
    -0.06
    inci
    -0.06
     booth
    -0.06
    &M
    -0.06
    htar
    -0.06
    <State
    -0.06
     entries
    -0.06
     Jac
    -0.06
     Hood
    -0.06
    POSITIVE LOGITS
    '>".$
    0.07
    .GetComponent
    0.07
     Homeland
    0.07
     Nowadays
    0.07
     bilgileri
    0.07
    DidEnter
    0.07
     unders
    0.06
     gé
    0.06
    _blog
    0.06
    subscriber
    0.06
    Act Density 0.024%

    No Known Activations