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

    Neuronpedia

    INDEX
    Explanations

    iterator code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lamp
    -0.08
    support
    -0.08
    submit
    -0.07
    -0.07
    government
    -0.07
    -0.07
    conc
    -0.07
     Swing
    -0.07
    aunch
    -0.07
     Lamp
    -0.07
    POSITIVE LOGITS
    剩
    0.10
     restante
    0.09
     reserva
    0.09
    Remaining
    0.09
    แรง
    0.09
    -extra
    0.08
     sands
    0.08
    _remaining
    0.08
    ('(
    0.08
     Remaining
    0.08
    Act Density 0.004%
    No Known Activations