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

    Neuronpedia

    INDEX
    Explanations

    Input field placeholders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	cnt
    -0.07
    Sing
    -0.07
    Contain
    -0.06
    Transmission
    -0.06
     masculine
    -0.06
    	Rect
    -0.06
     느�
    -0.06
     Min
    -0.06
    录
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     placeholder
    0.08
    <br
    0.07
    èles
    0.06
    (Cl
    0.06
     fireplace
    0.06
    稍
    0.06
     mast
    0.06
    lya
    0.06
    ‪
    0.06
    IGO
    0.06
    Act Density 0.001%

    No Known Activations