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

    Neuronpedia

    INDEX
    Explanations

    generated, stereo, Services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ഃ
    0.50
    ▥
    0.48
    小时候
    0.46
     незна
    0.46
    ⚜
    0.46
     watercolors
    0.45
    的价格
    0.44
     కొంత
    0.44
     पोकेमॉन
    0.44
    कुछ
    0.44
    POSITIVE LOGITS
    DH
    0.44
     hunk
    0.44
    SPA
    0.42
    ixar
    0.41
    tro
    0.40
    BMC
    0.40
    version
    0.39
    stdio
    0.39
    erequisite
    0.39
    FLP
    0.39
    Act Density 0.005%

    No Known Activations