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

    Neuronpedia

    INDEX
    Explanations

    combining things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Snake
    -0.07
    }));↵↵
    -0.06
    ,…↵↵
    -0.06
     riding
    -0.06
     enslaved
    -0.06
    /find
    -0.06
     توق
    -0.06
    Senha
    -0.06
     shrink
    -0.06
     consegu
    -0.06
    POSITIVE LOGITS
    _BLEND
    0.07
     используют
    0.07
     mix
    0.07
    	error
    0.06
     rus
    0.06
     blend
    0.06
    +=
    0.06
     Lilly
    0.06
     mixes
    0.06
    _pts
    0.06
    Act Density 0.036%

    No Known Activations