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

    Neuronpedia

    INDEX
    Explanations

    general English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     COL
    -0.07
    handle
    -0.06
     carpets
    -0.06
    шли
    -0.06
    andReturn
    -0.06
     nachází
    -0.06
     retorno
    -0.06
     donna
    -0.06
     Battlefield
    -0.06
     nons
    -0.06
    POSITIVE LOGITS
    ymbols
    0.07
     içine
    0.07
    配
    0.07
     solution
    0.07
    ji
    0.06
     targeted
    0.06
     Pod
    0.06
    Initial
    0.06
    ergus
    0.06
    컨
    0.06
    Act Density 0.000%

    No Known Activations