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

    Neuronpedia

    INDEX
    Explanations

    game roles and control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .wait
    -0.06
     car
    -0.06
    _points
    -0.06
    	object
    -0.06
     hatred
    -0.06
     odd
    -0.06
    ixture
    -0.06
    波
    -0.06
     cap
    -0.06
     Strom
    -0.06
    POSITIVE LOGITS
     despite
    0.07
    frau
    0.06
    �
    0.06
     сум
    0.06
     billeder
    0.06
     разви
    0.06
    rats
    0.06
    ώρα
    0.06
     concess
    0.06
     hız
    0.06
    Act Density 0.013%

    No Known Activations