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

    Neuronpedia

    INDEX
    Explanations

    generate, account, Green

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pyx
    0.39
     о
    0.38
     Capitalism
    0.38
    ధి
    0.38
    拧
    0.38
     discriminator
    0.38
     осуществления
    0.37
     камень
    0.37
    融资
    0.37
    ängen
    0.36
    POSITIVE LOGITS
     decided
    0.42
    PartResult
    0.40
     Poir
    0.37
     вполне
    0.36
    ূট
    0.36
    Stderr
    0.36
     freak
    0.35
     Arg
    0.35
     १६
    0.35
    पूर्ति
    0.35
    Act Density 0.000%

    No Known Activations