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

    Neuronpedia

    INDEX
    Explanations

    on a surface

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     violent
    0.47
     championed
    0.46
     dealings
    0.44
     authorizing
    0.44
     bombings
    0.44
     purses
    0.42
     discredit
    0.42
     authorizes
    0.41
     insofar
    0.41
     संबोध
    0.41
    POSITIVE LOGITS
    platform
    0.66
    平台
    0.61
     platform
    0.57
    Platform
    0.56
     Platform
    0.56
     pedestal
    0.55
     платфор
    0.54
    基礎
    0.54
     Plattform
    0.53
    平台上
    0.53
    Act Density 0.076%

    No Known Activations