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

    Neuronpedia

    INDEX
    Explanations

    File photos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    世界
    -0.06
    =h
    -0.06
    Hot
    -0.06
     Axis
    -0.06
     Naughty
    -0.06
    795
    -0.06
    Sarah
    -0.06
    078
    -0.06
     Gro
    -0.06
    ắc
    -0.06
    POSITIVE LOGITS
    ….↵↵
    0.07
     devout
    0.07
    !”↵↵
    0.07
     unprecedented
    0.07
    ̂
    0.06
    .');↵↵
    0.06
     validar
    0.06
     uten
    0.06
     FALSE
    0.06
     registro
    0.06
    Act Density 0.003%

    No Known Activations