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

    Neuronpedia

    INDEX
    Explanations

    largely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     matchmaking
    -0.08
     ppl
    -0.07
     pussy
    -0.07
    드
    -0.07
    _TICK
    -0.07
    	vector
    -0.07
     cmd
    -0.07
     cows
    -0.06
    _prompt
    -0.06
     maple
    -0.06
    POSITIVE LOGITS
     largely
    0.08
     HERE
    0.07
     SUCH
    0.07
     Graham
    0.06
     estas
    0.06
     diminished
    0.06
     Generally
    0.06
    AGING
    0.06
     레이
    0.06
     hukuk
    0.06
    Act Density 0.004%

    No Known Activations