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

    Neuronpedia

    INDEX
    Explanations

    explaining 'a breakdown'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    입니다
    0.56
    에
    0.53
    that
    0.53
    with
    0.51
    less
    0.51
    You
    0.51
    That
    0.50
    With
    0.50
    .:
    0.50
    It
    0.49
    POSITIVE LOGITS
     fucking
    0.50
     fascinating
    0.49
     philosophical
    0.48
     freaking
    0.47
     decorated
    0.46
     eyes
    0.46
     glimmer
    0.45
     case
    0.45
     interesting
    0.45
     eventual
    0.44
    Act Density 1.572%

    No Known Activations