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

    Neuronpedia

    INDEX
    Explanations

    cer

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     profond
    0.48
     глуби
    0.47
     derin
    0.44
     sâu
    0.43
     deepest
    0.42
     deeper
    0.41
    ленно
    0.40
     profundo
    0.39
     गहरे
    0.38
    ūk
    0.38
    POSITIVE LOGITS
     Nikhil
    0.38
    CL
    0.38
    관계
    0.37
    Ernest
    0.36
     Carn
    0.35
    ERICK
    0.35
    Bloom
    0.35
    ट्टे
    0.35
    nacht
    0.35
    NEC
    0.34
    Act Density 0.000%

    No Known Activations