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

    Neuronpedia

    INDEX
    Explanations

    least, but, should, attacker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Handlung
    0.51
    lz
    0.50
     肩
    0.49
    𝖑
    0.47
     ២
    0.46
     Emulator
    0.45
    lor
    0.44
     ofstream
    0.44
     Raises
    0.44
    anhyd
    0.44
    POSITIVE LOGITS
    کی
    0.46
     cryptic
    0.46
    訒
    0.45
     shrink
    0.44
    قبل
    0.44
    Antes
    0.44
     shrunk
    0.44
    ونی
    0.44
    ARIOS
    0.43
    کار
    0.43
    Act Density 0.002%

    No Known Activations