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

    Neuronpedia

    INDEX
    Explanations

    introductions, instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )]
    -0.07
    ]<
    -0.07
     widers
    -0.07
    uent
    -0.07
     queridos
    -0.07
     BN
    -0.07
     اه
    -0.07
     شمار
    -0.07
     Poul
    -0.07
     Anc
    -0.07
    POSITIVE LOGITS
    그리고
    0.08
     Dor
    0.08
    .practice
    0.07
     fragments
    0.07
    �
    0.07
    Dor
    0.07
     jag
    0.07
    नि
    0.07
    เร
    0.07
     permission
    0.07
    Act Density 0.485%

    No Known Activations