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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    along
    -0.07
     formally
    -0.07
    桌上
    -0.07
    func
    -0.07
    xED
    -0.07
    .numpy
    -0.06
     sak
    -0.06
    饯
    -0.06
    拜师
    -0.06
    ensex
    -0.06
    POSITIVE LOGITS
     '';↵↵
    0.08
     Swim
    0.08
    Rules
    0.07
    一团
    0.07
    .");↵
    0.07
     gaps
    0.07
    ))↵↵
    0.07
    ();↵↵
    0.07
     INTERNAL
    0.07
    >({↵
    0.07
    Act Density 0.012%

    No Known Activations