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

    Neuronpedia

    INDEX
    Explanations

    radiation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cls
    -0.07
    (),
    -0.07
     {_
    -0.07
    غات
    -0.06
    Revision
    -0.06
    ジア
    -0.06
     assignments
    -0.06
    "]))
    -0.06
     kdo
    -0.06
    ))*
    -0.06
    POSITIVE LOGITS
    bam
    0.07
    forma
    0.07
     trom
    0.06
     Invite
    0.06
    министра
    0.06
    elerinin
    0.06
     сторону
    0.06
     conven
    0.06
     إي
    0.06
     instructed
    0.06
    Act Density 0.011%

    No Known Activations