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

    Neuronpedia

    INDEX
    Explanations

    OAuth client authorization flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     amni
    0.42
     Habs
    0.41
     болезни
    0.41
    Air
    0.40
     walkway
    0.40
    Sign
    0.40
     trache
    0.40
     Wireless
    0.39
     Walther
    0.39
     รัก
    0.38
    POSITIVE LOGITS
     grant
    0.82
    grant
    0.78
    ClientId
    0.77
     client
    0.76
     scopes
    0.75
    ClientID
    0.72
    clientId
    0.71
    scopes
    0.71
     clientId
    0.70
    client
    0.70
    Act Density 0.018%

    No Known Activations