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

    Neuronpedia

    INDEX
    Explanations

    fever

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    窈
    -0.08
    뷴
    -0.08
     running
    -0.07
     lanes
    -0.07
    阘
    -0.06
     spor
    -0.06
     tutor
    -0.06
     })
↵
    -0.06
    .size
    -0.06
    行李
    -0.06
    POSITIVE LOGITS
    הפך
    0.08
    appe
    0.07
    주민
    0.07
    assemble
    0.07
    _amt
    0.07
    יקים
    0.07
    optgroup
    0.07
    ቅ
    0.07
    _reverse
    0.07
     improperly
    0.07
    Act Density 0.033%

    No Known Activations