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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -fired
    -0.08
    受
    -0.08
    -oh
    -0.08
     imediato
    -0.08
     inmediato
    -0.07
    -one
    -0.07
     threatening
    -0.07
     workflow
    -0.07
    -force
    -0.07
    roq
    -0.07
    POSITIVE LOGITS
    classmethod
    0.11
    staticmethod
    0.10
     Static
    0.08
    _Instance
    0.08
    (cls
    0.08
     Instance
    0.08
    .Instance
    0.08
    .INSTANCE
    0.08
     мировой
    0.08
     Da
    0.08
    Act Density 0.015%

    No Known Activations