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

    Neuronpedia

    INDEX
    Explanations

    code, API, technical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     empty
    -0.07
     railing
    -0.07
    tics
    -0.07
     coment
    -0.06
     zost
    -0.06
    Harness
    -0.06
    _PRO
    -0.06
    izr
    -0.06
     MU
    -0.06
    šti
    -0.06
    POSITIVE LOGITS
    .done
    0.07
    価
    0.07
     muschi
    0.06
    [arg
    0.06
     shortest
    0.06
    _len
    0.06
     phiên
    0.06
    隔
    0.06
     retval
    0.06
     ‫
    0.06
    Act Density 0.071%

    No Known Activations