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

    Neuronpedia

    INDEX
    Explanations

    need not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.67
    1
    0.66
     A
    0.61
     area
    0.59
     ISS
    0.59
    0
    0.59
     and
    0.59
     IC
    0.59
     or
    0.59
     P
    0.58
    POSITIVE LOGITS
    of
    0.57
     praktisch
    0.55
     schön
    0.55
     nemus
    0.54
     schönsten
    0.50
    時尚
    0.50
     höch
    0.49
    sebastian
    0.49
    א
    0.49
    beautiful
    0.49
    Act Density 0.000%

    No Known Activations