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

    Neuronpedia

    INDEX
    Explanations

    Code and errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    色泽
    -0.07
    ocyte
    -0.07
     كذلك
    -0.07
    窠
    -0.07
    erokee
    -0.07
    cons
    -0.07
    ⓟ
    -0.06
    rzy
    -0.06
    vy
    -0.06
    errer
    -0.06
    POSITIVE LOGITS
     fieldName
    0.07
     Giov
    0.07
    (mp
    0.07
    影
    0.07
    ,obj
    0.07
    (actual
    0.07
    "struct
    0.07
    ales
    0.07
    /[
    0.07
    .twitter
    0.07
    Act Density 0.059%

    No Known Activations