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

    Neuronpedia

    INDEX
    Explanations

    Glen AI research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    forbidden
    0.56
    𝘦
    0.53
    ponding
    0.53
    뜬
    0.52
    yielding
    0.52
    clientWidth
    0.52
     ಅದನ್ನು
    0.51
    壃
    0.51
     חש
    0.50
    ''}
    0.50
    POSITIVE LOGITS
     tasks
    0.53
     Fees
    0.52
     is
    0.52
     risks
    0.50
     fees
    0.50
    团队
    0.49
    0.49
     shares
    0.49
     sessions
    0.47
    趋势
    0.46
    Act Density 0.000%

    No Known Activations