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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $row
    -0.08
    .Reflection
    -0.07
    ในว
    -0.06
     öne
    -0.06
    $headers
    -0.06
    �
    -0.06
     ulož
    -0.06
     elk
    -0.06
    ='%
    -0.06
     Laden
    -0.06
    POSITIVE LOGITS
    arma
    0.07
    _UNS
    0.07
    -design
    0.06
     insol
    0.06
     underestimate
    0.06
     delivers
    0.06
    SearchTree
    0.06
    Creat
    0.06
    inson
    0.06
     soud
    0.06
    Act Density 0.016%

    No Known Activations