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

    Neuronpedia

    INDEX
    Explanations

    hours, estimated, intentionally, spray

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enden
    0.53
     responders
    0.45
     lifegu
    0.45
    popo
    0.45
     healers
    0.45
    half
    0.44
    osomes
    0.44
     quarantined
    0.44
    emergency
    0.44
    Informe
    0.44
    POSITIVE LOGITS
    тету
    0.48
    帔
    0.45
    畋
    0.45
    匽
    0.44
     Productivity
    0.44
    題目
    0.44
     уют
    0.44
    зда
    0.43
    ل
    0.43
     Italiano
    0.43
    Act Density 0.004%

    No Known Activations