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

    Neuronpedia

    INDEX
    Explanations

    risk factor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vért
    0.43
    注意的是
    0.43
     antimicrobial
    0.39
     meningitis
    0.38
    kadang
    0.38
     hız
    0.37
     condensers
    0.37
     Ministerial
    0.37
    graphs
    0.36
     කා
    0.36
    POSITIVE LOGITS
    Copyright
    0.39
    瑰
    0.38
    ...\
    0.38
     brune
    0.38
     sexy
    0.37
     pen
    0.37
     Pen
    0.37
    BAS
    0.37
     Convers
    0.36
     seduced
    0.36
    Act Density 0.000%

    No Known Activations