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

    Neuronpedia

    INDEX
    Explanations

    Dates in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	LP
    -0.07
    /Create
    -0.07
     jm
    -0.06
    Sem
    -0.06
     overtime
    -0.06
    _TOTAL
    -0.06
     Mama
    -0.06
     inserts
    -0.06
     Gorgeous
    -0.06
    civil
    -0.06
    POSITIVE LOGITS
    veedor
    0.06
     workout
    0.06
    igham
    0.06
    869
    0.06
    374
    0.06
    зано
    0.06
    演
    0.06
    ิร
    0.06
    ynos
    0.06
     predis
    0.06
    Act Density 0.008%

    No Known Activations