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

    Neuronpedia

    INDEX
    Explanations

    Building issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     walked
    -0.07
     Gallagher
    -0.07
    veral
    -0.07
    ्तन
    -0.06
     Years
    -0.06
     bits
    -0.06
    arna
    -0.06
     demise
    -0.06
    พร
    -0.06
     Ding
    -0.06
    POSITIVE LOGITS
    _STAGE
    0.07
     cận
    0.06
    _streams
    0.06
    cripcion
    0.06
     досяг
    0.06
     hairy
    0.06
    .checkNotNull
    0.06
     METH
    0.06
     nameof
    0.06
     бач
    0.06
    Act Density 0.026%

    No Known Activations