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

    Neuronpedia

    INDEX
    Explanations

    animal facts urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     VG
    0.43
    ypter
    0.40
    azz
    0.39
     gilt
    0.38
    캡
    0.38
     škol
    0.38
    schule
    0.38
     SignUp
    0.37
     شوی
    0.37
     _|
    0.37
    POSITIVE LOGITS
     bezig
    0.43
    χής
    0.42
    MAPE
    0.40
     ምን
    0.40
    ദാ
    0.40
    preprocess
    0.38
    proc
    0.38
    product
    0.37
    ibm
    0.37
    stocks
    0.37
    Act Density 0.000%

    No Known Activations