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

    Neuronpedia

    INDEX
    Explanations

    Physical layers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VM
    -0.08
    Forms
    -0.07
     Lists
    -0.06
     IP
    -0.06
    $b
    -0.06
    _SELF
    -0.06
    Movie
    -0.06
     mkdir
    -0.06
     comprar
    -0.06
    cession
    -0.06
    POSITIVE LOGITS
     conquer
    0.07
    //--
    0.06
    杂
    0.06
    -reaching
    0.06
     setStatus
    0.06
    -expanded
    0.06
     aş
    0.06
     ‐
    0.06
    �
    0.06
    .RESET
    0.06
    Act Density 0.044%

    No Known Activations