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

    Neuronpedia

    INDEX
    Explanations

    the massive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cruciate
    0.49
     Inhibition
    0.44
    ەتی
    0.43
    :
    0.43
    ፦
    0.42
     Inu
    0.42
     وإن
    0.41
     ہیں
    0.41
     penal
    0.40
     chromosome
    0.40
    POSITIVE LOGITS
    Air
    0.47
    Separ
    0.45
    dm
    0.44
    Volt
    0.44
    昂
    0.44
    рист
    0.42
    dlj
    0.42
    Network
    0.41
    Earth
    0.41
     огром
    0.41
    Act Density 5.456%

    No Known Activations