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

    Neuronpedia

    INDEX
    Explanations

    neurons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kte
    -0.07
    washing
    -0.07
     PdfP
    -0.07
    alist
    -0.07
    acock
    -0.06
     gdk
    -0.06
    ickle
    -0.06
    IFEST
    -0.06
     dietary
    -0.06
    agency
    -0.06
    POSITIVE LOGITS
     neurons
    0.16
     neuron
    0.11
    on
    0.08
    urons
    0.07
    ON
    0.07
     немного
    0.07
     الملك
    0.07
    _neurons
    0.07
     Hern
    0.06
    نان
    0.06
    Act Density 0.005%

    No Known Activations