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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Deque
    -0.06
    pletely
    -0.06
     honorary
    -0.06
     jus
    -0.06
    _An
    -0.06
     classmates
    -0.06
    FullPath
    -0.06
     expire
    -0.06
     بر
    -0.05
     приб
    -0.05
    POSITIVE LOGITS
    leading
    0.08
    ๕
    0.07
    --------------------
    0.07
    ْم
    0.07
     −
    0.07
    .compile
    0.07
    ---------------
    0.06
    abee
    0.06
     VERIFY
    0.06
    ículos
    0.06
    Act Density 0.015%

    No Known Activations