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

    Neuronpedia

    INDEX
    Explanations

    Action

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Legisl
    -0.08
     CVS
    -0.08
     semif
    -0.07
     robbery
    -0.07
    avis
    -0.07
    柒
    -0.07
    房车
    -0.07
    仨
    -0.07
     Pulitzer
    -0.07
    their
    -0.07
    POSITIVE LOGITS
    .Pointer
    0.07
    芳香
    0.07
    �
    0.07
    ...')↵
    0.07
    ToDelete
    0.07
     자연
    0.07
    .hm
    0.06
    UILTIN
    0.06
    颤
    0.06
    嫕
    0.06
    Act Density 0.001%

    No Known Activations