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

    Neuronpedia

    INDEX
    Explanations

    ANY

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atorial
    -0.06
    	UP
    -0.06
    -\
    -0.06
     strpos
    -0.06
     orth
    -0.06
    CO
    -0.06
     bull
    -0.06
    adv
    -0.06
     acting
    -0.06
     Pur
    -0.06
    POSITIVE LOGITS
    LOPT
    0.08
     اشاره
    0.07
    λον
    0.07
     подроб
    0.07
     Loves
    0.06
    .Track
    0.06
     سلس
    0.06
    無
    0.06
    -pattern
    0.06
    لمه
    0.06
    Act Density 0.001%

    No Known Activations