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

    Neuronpedia

    INDEX
    Explanations

    Meta explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    提交
    0.46
     rodziny
    0.46
     Joining
    0.45
     کشور
    0.44
     केसर
    0.44
     причиной
    0.44
    ुल्लाह
    0.44
    υτό
    0.43
     Necessary
    0.43
     preparado
    0.43
    POSITIVE LOGITS
     indis
    0.46
     usi
    0.46
     defini
    0.43
    pir
    0.43
     undeniable
    0.43
     indulgent
    0.43
    獣
    0.43
     fini
    0.42
    ments
    0.42
    ird
    0.41
    Act Density 0.001%

    No Known Activations