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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Summer
    -0.07
     programmers
    -0.06
     Winter
    -0.06
     apprentice
    -0.06
    picable
    -0.06
     lantern
    -0.06
    ajor
    -0.06
    圳
    -0.06
    .Contact
    -0.06
     angry
    -0.06
    POSITIVE LOGITS
    نى
    0.08
    �
    0.07
    porter
    0.06
    Frames
    0.06
     navy
    0.06
    _empresa
    0.06
    سة
    0.06
    ,str
    0.06
     zemi
    0.06
    ování
    0.06
    Act Density 0.047%

    No Known Activations