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

    Neuronpedia

    INDEX
    Explanations

    opinion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -backend
    -0.07
    	obj
    -0.06
     Rud
    -0.06
    CLUDE
    -0.06
     keys
    -0.06
    627
    -0.06
    ключ
    -0.06
     thanked
    -0.06
    илання
    -0.06
     prematurely
    -0.06
    POSITIVE LOGITS
    ={{
    0.06
     rout
    0.06
     Quinn
    0.06
    )="
    0.06
    ]");↵
    0.06
    .Checked
    0.06
     ""}↵
    0.06
    誉
    0.06
    --}}↵
    0.06
    .internal
    0.06
    Act Density 0.022%

    No Known Activations