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

    Neuronpedia

    INDEX
    Explanations

    cre

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Frozen
    0.45
    frozen
    0.45
    ریس
    0.43
    Frozen
    0.43
    Cheese
    0.39
    рай
    0.38
    release
    0.38
    Runner
    0.38
     froze
    0.38
    eol
    0.37
    POSITIVE LOGITS
    VB
    0.41
    OPHY
    0.39
     lush
    0.37
    קט
    0.37
    注重
    0.37
    nhof
    0.36
    SystemService
    0.36
     gegründet
    0.35
    泱
    0.35
    ্যাশ
    0.34
    Act Density 0.000%

    No Known Activations