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

    Neuronpedia

    INDEX
    Explanations

    Timestamps and time formats

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝙎
    -0.08
    新鲜
    -0.07
    써
    -0.07
     clos
    -0.07
     holes
    -0.07
     сообщ
    -0.07
    磋商
    -0.07
    @s
    -0.07
     Science
    -0.06
    .client
    -0.06
    POSITIVE LOGITS
    颜值
    0.08
    _DISPLAY
    0.07
    .Log
    0.07
    _PANEL
    0.07
    _BACKEND
    0.07
    riangle
    0.06
     skins
    0.06
     NEVER
    0.06
    _MED
    0.06
    雒
    0.06
    Act Density 0.024%

    No Known Activations