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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’a
    -0.07
    าคม
    -0.07
     subset
    -0.06
     Kü
    -0.06
    .click
    -0.06
    ymous
    -0.06
    363
    -0.06
    .mean
    -0.06
    těž
    -0.06
     Suff
    -0.06
    POSITIVE LOGITS
     when
    0.09
     ds
    0.08
     pioneered
    0.06
    ablish
    0.06
    .pag
    0.06
     Content
    0.06
    เ�
    0.06
     numar
    0.06
    ulo
    0.06
    inance
    0.06
    Act Density 0.039%

    No Known Activations