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

    Neuronpedia

    INDEX
    Explanations

    access security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    infinity
    0.45
     infinity
    0.40
    着
    0.39
    arial
    0.38
                    
    0.38
    হা
    0.38
    iquity
    0.38
    绮
    0.37
     narrowly
    0.37
     Elig
    0.37
    POSITIVE LOGITS
     compañeros
    0.43
    PopMatrix
    0.40
     शिष्य
    0.40
     होम्योपै
    0.38
     realizzazione
    0.38
     UTIL
    0.38
    می
    0.37
    끔
    0.37
     creazione
    0.37
     Spots
    0.36
    Act Density 0.000%

    No Known Activations