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

    Neuronpedia

    INDEX
    Explanations

    play

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gravity
    -0.07
    /git
    -0.06
    	BOOST
    -0.06
     clients
    -0.06
     Chemical
    -0.06
    _locale
    -0.06
    學院
    -0.06
    BUF
    -0.06
     threshold
    -0.06
     kernel
    -0.06
    POSITIVE LOGITS
     pylint
    0.07
    _ground
    0.07
     mant
    0.06
    нед
    0.06
     Haut
    0.06
     urge
    0.06
    odě
    0.06
    岩
    0.06
    .ToolTip
    0.06
    mAh
    0.06
    Act Density 0.008%

    No Known Activations