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

    Neuronpedia

    INDEX
    Explanations

    Undeniable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ylül
    -0.08
    クラブ
    -0.07
     pageCount
    -0.06
    \Image
    -0.06
    (f
    -0.06
     공고
    -0.06
     accessories
    -0.06
     skept
    -0.06
     Keep
    -0.06
    Finish
    -0.06
    POSITIVE LOGITS
     undis
    0.07
     undoubtedly
    0.07
     undeniable
    0.07
    因
    0.07
     unquestion
    0.07
    控
    0.06
     regeneration
    0.06
     registrado
    0.06
     needless
    0.06
    当
    0.06
    Act Density 0.005%

    No Known Activations