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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.77
     '{@
    -0.65
    semantics
    -0.59
    towany
    -0.50
     getItemId
    -0.49
     utafitiHapana
    -0.48
    ICED
    -0.47
     leta
    -0.47
    aside
    -0.47
    äns
    -0.46
    POSITIVE LOGITS
     varied
    0.56
     diverse
    0.55
     different
    0.54
     různ
    0.54
     varying
    0.53
     unterschiedlich
    0.52
     ComVisible
    0.52
    BufferException
    0.52
     juger
    0.51
     GenerationType
    0.51
    Act Density 0.005%

    No Known Activations