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

    Neuronpedia

    INDEX
    Explanations

    Formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UserData
    -0.08
    Latitude
    -0.07
     cryptoc
    -0.07
     setType
    -0.07
    תן
    -0.07
    引用日期
    -0.07
     IAM
    -0.06
     תוכנ
    -0.06
    曙光
    -0.06
    	sound
    -0.06
    POSITIVE LOGITS
     binge
    0.08
     allergies
    0.07
     transgender
    0.07
    大的
    0.07
     grilled
    0.07
     engineered
    0.07
     BUFFER
    0.07
    girl
    0.07
     invoke
    0.07
    -secret
    0.07
    Act Density 0.210%

    No Known Activations