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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Their
    -0.06
    PH
    -0.06
     pw
    -0.06
    For
    -0.06
    	u
    -0.06
    ющих
    -0.06
     Free
    -0.06
    hatt
    -0.06
     lua
    -0.06
    ']");↵
    -0.06
    POSITIVE LOGITS
    -target
    0.07
    IRC
    0.06
    ออ
    0.06
     dors
    0.06
     viewport
    0.06
     dough
    0.06
    �
    0.06
    gregated
    0.06
     Doors
    0.06
    _parameter
    0.06
    Act Density 0.010%

    No Known Activations