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

    Neuronpedia

    INDEX
    Explanations

    hypothetical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ans
    -0.07
    appName
    -0.07
    .ONE
    -0.07
    istra
    -0.07
     Zoe
    -0.07
    军
    -0.07
    issance
    -0.07
    海底
    -0.07
     soldier
    -0.07
     стало
    -0.07
    POSITIVE LOGITS
     Div
    0.08
    𝄱
    0.07
    ">'.$
    0.07
     Cute
    0.07
     redraw
    0.07
     Retro
    0.07
     Each
    0.07
     exhibited
    0.06
    ])),
    0.06
    0.06
    Act Density 0.003%

    No Known Activations