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

    Neuronpedia

    INDEX
    Explanations

    math word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мүмкіндік
    -0.09
     SIST
    -0.08
     шығарм
    -0.08
     CONSEQUENTIAL
    -0.08
     жақ
    -0.08
     tonic
    -0.08
     жоғары
    -0.08
     ɛ
    -0.08
     konuda
    -0.08
     pagkakata
    -0.08
    POSITIVE LOGITS
    単
    0.08
    Observed
    0.08
    观察
    0.07
     observed
    0.07
     Received
    0.07
    Received
    0.07
    单位
    0.07
    Referenced
    0.07
     Appar
    0.07
    Extractor
    0.07
    Act Density 0.051%

    No Known Activations