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

    Neuronpedia

    INDEX
    Explanations

    holding steady, dynamic programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    0.55
     conflicts
    0.51
     de
    0.47
     flam
    0.46
     Conflicts
    0.46
     i
    0.46
     devolution
    0.46
     Conflict
    0.45
    Conflict
    0.45
    to
    0.44
    POSITIVE LOGITS
    ದ್ಯ
    0.54
    வட
    0.52
     scoperto
    0.50
     ಪ್ಯಾ
    0.48
     entertainers
    0.47
     Ζ
    0.47
    dimensioni
    0.47
    ופ
    0.47
    メートル
    0.47
     Σε
    0.46
    Act Density 0.000%

    No Known Activations