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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rhyme
    -0.08
    �
    -0.07
    如同
    -0.07
    .photos
    -0.07
     środowisk
    -0.07
    👖
    -0.07
    bye
    -0.07
    DFS
    -0.07
    بارك
    -0.07
    𖠚
    -0.06
    POSITIVE LOGITS
     повер
    0.07
     warranted
    0.07
    >())
    0.07
    orthy
    0.07
     соглас
    0.07
    县委
    0.07
     Column
    0.06
    >")
    0.06
    )?;↵↵
    0.06
     ());↵↵
    0.06
    Act Density 0.007%

    No Known Activations