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

    Neuronpedia

    INDEX
    Explanations

    databases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     byt
    -0.08
     souhlas
    -0.08
     arguing
    -0.07
     ware
    -0.07
     heightened
    -0.07
     RTP
    -0.06
     sple
    -0.06
    ysical
    -0.06
     Binary
    -0.06
     전에
    -0.06
    POSITIVE LOGITS
    Looking
    0.06
     };
↵
↵
    0.06
     баж
    0.06
     stumble
    0.06
    »↵↵
    0.06
     barley
    0.06
    	Type
    0.06
    herent
    0.06
    ेण
    0.06
     επα
    0.06
    Act Density 0.017%

    No Known Activations