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

    Neuronpedia

    INDEX
    Explanations

    44

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    slope
    -0.08
     symmetry
    -0.06
     hole
    -0.06
     chant
    -0.06
    /meta
    -0.06
    isode
    -0.06
     methane
    -0.06
     machining
    -0.06
     muscle
    -0.06
    et
    -0.06
    POSITIVE LOGITS
    42
    0.10
    43
    0.09
    44
    0.08
    41
    0.08
    0.08
    45
    0.08
    ipeg
    0.08
    46
    0.08
    ancouver
    0.08
    opot
    0.07
    Act Density 0.072%

    No Known Activations