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

    Neuronpedia

    INDEX
    Explanations

    encoded/random strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inue
    -0.08
    باء
    -0.08
    ائح
    -0.08
     Marie
    -0.08
    -hand
    -0.08
     Stéph
    -0.07
    -liquid
    -0.07
    IPE
    -0.07
    keras
    -0.07
     remarkable
    -0.07
    POSITIVE LOGITS
     Madness
    0.11
    ellaneous
    0.09
    intosh
    0.09
     Twin
    0.09
    /MS
    0.08
    ikhail
    0.08
     Hunter
    0.08
     hunter
    0.08
    esota
    0.08
    embros
    0.08
    Act Density 0.720%

    No Known Activations