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

    Neuronpedia

    INDEX
    Explanations

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @@@@
    -0.06
    ��
    -0.06
    seudo
    -0.06
     parity
    -0.06
    {s
    -0.06
    ---
    -0.06
    Cou
    -0.06
     pots
    -0.06
    Allen
    -0.06
     сух
    -0.06
    POSITIVE LOGITS
     physique
    0.08
    pcion
    0.07
    GN
    0.07
    _NEAR
    0.07
    uridad
    0.06
    _View
    0.06
     infield
    0.06
    .case
    0.06
     vigil
    0.06
     arresting
    0.06
    Act Density 0.070%

    No Known Activations