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

    Neuronpedia

    INDEX
    Explanations

    non-chill filtered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vínculos
    0.64
     arquivos
    0.63
    czą
    0.58
     oppress
    0.55
     humaines
    0.55
     lignes
    0.54
     entwickelt
    0.53
     лінії
    0.52
    govern
    0.52
     allez
    0.51
    POSITIVE LOGITS
    ien
    0.46
     Dr
    0.46
    ime
    0.46
    cken
    0.45
    mos
    0.45
     Astronomy
    0.44
    ley
    0.44
    mi
    0.43
    ibilit
    0.43
     Port
    0.43
    Act Density 0.000%

    No Known Activations