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

    Neuronpedia

    INDEX
    Explanations

    credentials and systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ма
    0.54
    湖
    0.49
    f
    0.47
    atelle
    0.47
    、
    0.46
    indentLevel
    0.46
    蛇
    0.46
    гне
    0.45
    Runtime
    0.43
    Pas
    0.43
    POSITIVE LOGITS
     describir
    0.53
     dha
    0.52
     Dmit
    0.49
     tienden
    0.48
    isc
    0.46
     छोर
    0.46
     ರಾಜ್ಯ
    0.46
     ener
    0.46
     rikt
    0.46
     COLLEGE
    0.46
    Act Density 0.000%

    No Known Activations