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

    Neuronpedia

    INDEX
    Explanations

    apologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Todd
    -0.07
    Vtbl
    -0.07
    (ctx
    -0.07
    ༚
    -0.07
    _phys
    -0.07
    _head
    -0.06
    ebb
    -0.06
    משקיע
    -0.06
    Present
    -0.06
     Checkout
    -0.06
    POSITIVE LOGITS
    (media
    0.07
    ANGER
    0.07
    Ρ
    0.07
    .H
    0.07
    Mo
    0.07
    (categories
    0.07
     growers
    0.07
     lc
    0.07
    دل
    0.06
     메
    0.06
    Act Density 0.004%

    No Known Activations