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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ოუ�
    -0.08
    wicklung
    -0.08
    ունդ
    -0.08
    ტერეს
    -0.08
     احساس
    -0.08
     যোগ
    -0.08
     Wonderland
    -0.08
     ենթ
    -0.08
     gusto
    -0.08
    beaut
    -0.08
    POSITIVE LOGITS
     boundaries
    0.09
     walls
    0.07
     constraints
    0.07
    Constraints
    0.07
     regras
    0.07
    constraints
    0.07
    (Border
    0.07
     barr
    0.07
     lijnen
    0.07
     borders
    0.07
    Act Density 0.010%

    No Known Activations