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

    Neuronpedia

    INDEX
    Explanations

    Code and conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATFORM
    -0.07
     Electoral
    -0.07
    ieces
    -0.07
    áhnout
    -0.07
    _Search
    -0.07
    ष
    -0.06
    .sponge
    -0.06
    _FAILED
    -0.06
     ECC
    -0.06
     catches
    -0.06
    POSITIVE LOGITS
    ',"
    0.07
     질문
    0.06
     >",
    0.06
    ograph
    0.06
    cntl
    0.06
    _ENDPOINT
    0.06
     πρά
    0.06
    (person
    0.06
     Obj
    0.06
    etections
    0.06
    Act Density 0.000%

    No Known Activations