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

    Neuronpedia

    INDEX
    Explanations

    proper names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Keci
    0.41
     PvP
    0.40
     Firmware
    0.39
    랫폼
    0.39
     copyspace
    0.38
     VHF
    0.37
     Ecusson
    0.37
    smöglichkeiten
    0.36
     Sereth
    0.36
     tetragonal
    0.36
    POSITIVE LOGITS
    z
    0.49
    j
    0.47
    r
    0.44
    h
    0.43
    on
    0.43
    man
    0.43
    ley
    0.42
    l
    0.42
    ch
    0.42
    in
    0.41
    Act Density 0.020%

    No Known Activations