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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    svn
    -0.06
    fahren
    -0.06
    Checkpoint
    -0.06
    REAK
    -0.06
    MUX
    -0.06
    άσ
    -0.06
    _minimum
    -0.06
    .Headers
    -0.06
    inant
    -0.06
    /Area
    -0.06
    POSITIVE LOGITS
     �
    0.07
     컨
    0.07
     ruta
    0.06
    Scheme
    0.06
    [arg
    0.06
    ']]↵
    0.06
     Hammond
    0.06
     skoro
    0.06
    uers
    0.06
    flies
    0.06
    Act Density 0.200%

    No Known Activations