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
    .tv
    -0.07
     Тур
    -0.07
     tracker
    -0.07
    อบ
    -0.07
    oshi
    -0.07
    っち
    -0.07
    郫
    -0.07
    ."""
    -0.07
    =res
    -0.07
    ཡ
    -0.07
    POSITIVE LOGITS
    )↵↵
    0.08
     frü
    0.07
    )↵
    0.07
    隐患
    0.07
     grease
    0.07
    MetaData
    0.06
     verschied
    0.06
     roles
    0.06
     evaluations
    0.06
     antics
    0.06
    Act Density 0.109%

    No Known Activations