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

    Neuronpedia

    INDEX
    Explanations

    Polls and surveys

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     claim
    -0.07
    ologist
    -0.07
     decides
    -0.07
     justified
    -0.06
     monitor
    -0.06
     softball
    -0.06
     claims
    -0.06
     filmed
    -0.06
     develops
    -0.06
     election
    -0.06
    POSITIVE LOGITS
     strtol
    0.07
    ilters
    0.06
     cess
    0.06
     가족
    0.06
     خانو
    0.06
     Гол
    0.06
     ama
    0.06
    .TestCheck
    0.06
    ुकस
    0.06
    ificent
    0.06
    Act Density 0.012%

    No Known Activations