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

    Neuronpedia

    INDEX
    Explanations

    ruins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ontrol
    -0.08
    (video
    -0.07
    paramref
    -0.07
    Github
    -0.07
    Introduction
    -0.07
    ')).
    -0.07
     zdrav
    -0.07
    ’ta
    -0.06
    Scheme
    -0.06
     azt
    -0.06
    POSITIVE LOGITS
     ruins
    0.07
     debris
    0.07
     vicinity
    0.06
     Kern
    0.06
    ularity
    0.06
     rubble
    0.06
     remnants
    0.06
    rpc
    0.06
     microbi
    0.06
    nant
    0.06
    Act Density 0.017%

    No Known Activations