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

    Neuronpedia

    INDEX
    Explanations

    creating examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ेत
    -0.07
    _form
    -0.06
    Languages
    -0.06
    Processor
    -0.06
    /ap
    -0.06
     çevres
    -0.06
    warz
    -0.06
    _med
    -0.06
    IZER
    -0.06
    KeyName
    -0.06
    POSITIVE LOGITS
    carrier
    0.07
     HACK
    0.06
     collapses
    0.06
     RTL
    0.06
    transforms
    0.06
    sterreich
    0.06
    оит
    0.06
     jar
    0.06
    �
    0.06
    layer
    0.06
    Act Density 0.039%

    No Known Activations