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

    Neuronpedia

    INDEX
    Explanations

    company needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ratio
    0.44
     SMI
    0.39
    ফতার
    0.38
     ис
    0.37
    Data
    0.37
    码
    0.36
    尺寸
    0.36
    []){
    0.36
     spiritually
    0.36
    Desc
    0.35
    POSITIVE LOGITS
    াব
    0.46
    ongan
    0.44
     spoke
    0.44
     gesprochen
    0.44
     jednotliv
    0.43
    اہر
    0.43
     speaks
    0.42
    ührt
    0.42
    anzit
    0.42
     भेट
    0.42
    Act Density 0.000%

    No Known Activations