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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tires
    -0.08
     Seats
    -0.07
     Objects
    -0.07
    好像
    -0.07
    	get
    -0.07
     surviving
    -0.06
    _on
    -0.06
     돈
    -0.06
     spokesperson
    -0.06
    _upd
    -0.06
    POSITIVE LOGITS
    vf
    0.07
     �
    0.06
     ComponentFixture
    0.06
    atri
    0.06
     раза
    0.06
    -view
    0.06
    Ve
    0.06
     jobId
    0.06
     RaycastHit
    0.06
     출
    0.06
    Act Density 0.009%

    No Known Activations