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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    祉
    -0.07
    סטודנט
    -0.07
    沪深
    -0.07
     אות
    -0.07
    -ion
    -0.07
     проб
    -0.06
    ovenant
    -0.06
    곸
    -0.06
     acronym
    -0.06
    屆
    -0.06
    POSITIVE LOGITS
     Target
    0.09
     ret
    0.07
     testing
    0.07
     TESTING
    0.07
     wheels
    0.07
     Disco
    0.07
     EXPER
    0.07
    Tre
    0.07
     Sara
    0.06
    (CONT
    0.06
    Act Density 0.034%

    No Known Activations