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

    Neuronpedia

    INDEX
    Explanations

    great

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Provide
    -0.06
     �
    -0.06
    (str
    -0.06
     Kevin
    -0.06
     Kelvin
    -0.06
    Switch
    -0.06
    	Start
    -0.06
    /th
    -0.06
     فرد
    -0.06
     jail
    -0.06
    POSITIVE LOGITS
     fc
    0.07
    ा।
    0.07
     今
    0.06
     Biblical
    0.06
     snaží
    0.06
     Orleans
    0.06
     Cue
    0.06
     {}).
    0.06
    .hstack
    0.06
     berth
    0.06
    Act Density 0.071%

    No Known Activations