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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cybersecurity
    -0.07
    _ZERO
    -0.06
    $"
    -0.06
    Adj
    -0.06
    Past
    -0.06
    deny
    -0.05
     Pete
    -0.05
     dyn
    -0.05
    &eacute
    -0.05
     сх
    -0.05
    POSITIVE LOGITS
     몰
    0.08
    Callable
    0.08
    (cluster
    0.07
     Jong
    0.07
     غذ
    0.07
    �
    0.06
     Queries
    0.06
    :pointer
    0.06
     ấn
    0.06
    322
    0.06
    Act Density 0.026%

    No Known Activations