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

    Neuronpedia

    INDEX
    Explanations

    Equations and formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Depends
    -0.07
     Singles
    -0.06
    _func
    -0.06
    -west
    -0.06
    ая
    -0.06
    ila
    -0.06
     paperback
    -0.06
    (print
    -0.06
    uyên
    -0.06
    rians
    -0.06
    POSITIVE LOGITS
     Smash
    0.07
    _CONTROL
    0.06
    	cal
    0.06
    stroy
    0.06
     Constr
    0.06
    brid
    0.06
     :],
    0.06
     blot
    0.06
    roi
    0.06
    )})
    0.06
    Act Density 0.063%

    No Known Activations