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

    Neuronpedia

    INDEX
    Explanations

    Miss or Continued

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ണം
    0.66
     пищи
    0.63
     inwoners
    0.63
    isAssignableFrom
    0.63
     afbeelding
    0.61
     ē
    0.60
     красоты
    0.60
    DebugType
    0.59
     BatchNorm
    0.59
     zawsze
    0.59
    POSITIVE LOGITS
    Miss
    0.61
    ımın
    0.56
    我还
    0.56
    Seeing
    0.55
     Miss
    0.55
    amal
    0.55
    Democratic
    0.54
     observed
    0.54
    Caught
    0.53
     board
    0.53
    Act Density 0.000%

    No Known Activations