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
    ises
    -0.07
    ruptions
    -0.06
    anyak
    -0.06
     hatch
    -0.06
    イト
    -0.06
     Nil
    -0.06
    Ingredient
    -0.06
    enefit
    -0.06
     درست
    -0.06
    уются
    -0.06
    POSITIVE LOGITS
     boy
    0.07
    probe
    0.06
    LESS
    0.06
    Ο�
    0.06
     bloggers
    0.06
     του
    0.06
     nb
    0.06
    _ratio
    0.06
    _ring
    0.06
     documenting
    0.06
    Act Density 0.083%

    No Known Activations