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

    Neuronpedia

    INDEX
    Explanations

    entry points or fees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.71
    T
    0.65
    ’
    0.64
    D
    0.58
    N
    0.55
    P
    0.52
     titleImageUrl
    0.51
    '=>$
    0.49
    PA
    0.48
    рел
    0.48
    POSITIVE LOGITS
    the
    0.54
     the
    0.51
    ativas
    0.44
     reentry
    0.44
      
    0.44
    necks
    0.44
    Not
    0.43
    arm
    0.42
    entrée
    0.42
    begin
    0.42
    Act Density 0.012%

    No Known Activations