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

    Neuronpedia

    INDEX
    Explanations

    curved shapes and directional movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    curved shapes

    np_acts-logits-general · gemini-2.0-flash

    curved surfaces, paths, and shapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    };*/
    -0.60
    });*/
    -0.59
    ---*/
    -0.58
     pores
    -0.57
    ();*/
    -0.56
    Marshal
    -0.55
     EdgeInsets
    -0.55
     onPostExecute
    -0.55
    धारण
    -0.54
    """
    -0.54
    POSITIVE LOGITS
     bends
    0.88
     curved
    0.83
     crooked
    0.83
     Bent
    0.81
     bend
    0.80
     angles
    0.79
    AndEndTag
    0.78
     angle
    0.78
    curved
    0.77
    Bent
    0.77
    Act Density 0.364%

    No Known Activations