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

    Neuronpedia

    INDEX
    Explanations

    technical/programming language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ipe
    -0.07
     count
    -0.07
    يرة
    -0.07
     tooltip
    -0.07
    pression
    -0.07
     drowning
    -0.06
     column
    -0.06
     bigot
    -0.06
    	lp
    -0.06
    Letters
    -0.06
    POSITIVE LOGITS
     FName
    0.06
    ("/{
    0.06
     Inflate
    0.06
    (ray
    0.06
     kre
    0.05
    POR
    0.05
     Rel
    0.05
    vertiser
    0.05
     Giz
    0.05
     Zealand
    0.05
    Act Density 0.005%

    No Known Activations