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

    Neuronpedia

    INDEX
    Explanations

    pre-programmed responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Intern
    0.42
    setInt
    0.42
    шуу
    0.41
    AddModel
    0.40
     اختی
    0.40
     pertence
    0.39
     admite
    0.38
     исполнения
    0.38
    zuc
    0.38
    Everybody
    0.37
    POSITIVE LOGITS
    灣
    0.40
    湾
    0.38
    門
    0.37
    வம்
    0.36
     Ray
    0.36
     Cork
    0.36
     thriving
    0.35
    Template
    0.35
     nerve
    0.35
    が得
    0.35
    Act Density 0.000%

    No Known Activations