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

    Neuronpedia

    INDEX
    Explanations

    349

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bail
    -0.08
    AAF
    -0.07
     tether
    -0.07
     Neville
    -0.07
     Natalie
    -0.07
    ểm
    -0.07
     leap
    -0.07
    observ
    -0.06
     Bene
    -0.06
     Heath
    -0.06
    POSITIVE LOGITS
    250
    0.12
    150
    0.10
    351
    0.10
    251
    0.09
    652
    0.09
    651
    0.09
    �
    0.08
    752
    0.08
    850
    0.08
    751
    0.08
    Act Density 0.116%

    No Known Activations