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

    Neuronpedia

    INDEX
    Explanations

    want to do / 하고 싶으신지

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蒯
    0.40
    మై
    0.39
    ImageData
    0.38
    पुरा
    0.37
     বছর
    0.37
    二十
    0.37
    Writes
    0.37
    Kate
    0.36
     sentimientos
    0.36
     வாங்க
    0.36
    POSITIVE LOGITS
     correspon
    0.38
     결정
    0.37
     kem
    0.37
    devel
    0.37
    膏
    0.36
    optimization
    0.36
    cient
    0.35
     ಅದನ್ನು
    0.35
    proficiency
    0.35
     corresponding
    0.35
    Act Density 0.000%

    No Known Activations