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

    Neuronpedia

    INDEX
    Explanations

    ***

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    ='".$
    -0.08
    يون
    -0.07
     Larson
    -0.07
    粒
    -0.07
     '".$
    -0.07
    果然
    -0.07
    .Wh
    -0.07
    一笑
    -0.07
    终于
    -0.06
     elsewhere
    -0.06
    POSITIVE LOGITS
     Bard
    0.07
    cheduler
    0.07
    .misc
    0.07
    _IF
    0.07
     vim
    0.07
     flag
    0.07
     Intersection
    0.06
    шир
    0.06
     issuer
    0.06
     Showcase
    0.06
    Act Density 0.000%

    No Known Activations