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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igham
    -0.07
     setter
    -0.07
     Playboy
    -0.06
    abox
    -0.06
    .createUser
    -0.06
    ivan
    -0.06
    velopment
    -0.06
     Pharma
    -0.06
     Hosting
    -0.06
     racially
    -0.06
    POSITIVE LOGITS
     Freed
    0.07
    OKIE
    0.07
    (fontSize
    0.07
    ILLE
    0.06
    seq
    0.06
    .mouse
    0.06
    σταση
    0.06
     Fired
    0.06
    ATED
    0.06
    olie
    0.06
    Act Density 0.075%

    No Known Activations