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

    Neuronpedia

    INDEX
    Explanations

    contrasting conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anisotropy
    0.22
     isotherms
    0.22
     cytoskeleton
    0.22
     conformations
    0.22
     afflict
    0.22
     affliction
    0.21
     covariance
    0.21
     codons
    0.21
     equation
    0.20
     wafer
    0.20
    POSITIVE LOGITS
     However
    0.39
     परंतु
    0.35
     लेकिन
    0.35
     tuttavia
    0.34
    However
    0.33
     પરંતુ
    0.33
     however
    0.32
     কিন্তু
    0.31
     Однако
    0.31
     HOWEVER
    0.31
    Act Density 4.419%

    No Known Activations