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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ีช
    -0.07
     Parkway
    -0.07
     Sandwich
    -0.07
     �
    -0.06
    .ops
    -0.06
    284
    -0.06
    _win
    -0.06
     lettre
    -0.06
    (candidate
    -0.06
    .arc
    -0.06
    POSITIVE LOGITS
     lesions
    0.07
     Imam
    0.07
    ैल
    0.07
    _BAD
    0.07
    based
    0.06
    vascular
    0.06
    animations
    0.06
    but
    0.06
     banka
    0.06
    Ћ
    0.06
    Act Density 0.056%

    No Known Activations