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

    Neuronpedia

    INDEX
    Explanations

    code blocks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reproduce
    -0.08
    ca
    -0.07
    landırma
    -0.07
     tvar
    -0.06
     Matchers
    -0.06
     influencers
    -0.06
     bourgeois
    -0.06
    ับสน
    -0.06
     برابر
    -0.06
    uler
    -0.06
    POSITIVE LOGITS
    osate
    0.06
    _PC
    0.06
     Anatomy
    0.06
    ??↵↵
    0.06
    Charge
    0.06
    (contact
    0.06
    „P
    0.05
    Wheel
    0.05
    ]:↵↵
    0.05
    ==↵
    0.05
    Act Density 0.011%

    No Known Activations