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

    Neuronpedia

    INDEX
    Explanations

    input or inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     באי
    0.38
    }$;
    0.37
     notor
    0.34
    ]=='
    0.34
    Gravestone
    0.34
    ಜಿ
    0.33
     👇
    0.33
     ratus
    0.32
    Wars
    0.31
     warl
    0.31
    POSITIVE LOGITS
     inputs
    0.45
     Inputs
    0.41
    ர்ச்ச
    0.40
    freien
    0.38
    inputType
    0.37
    apture
    0.36
     Input
    0.36
    inputs
    0.36
     input
    0.35
     দ্বি
    0.35
    Act Density 0.000%

    No Known Activations