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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Singer
    -0.07
     Page
    -0.07
    .so
    -0.06
     Download
    -0.06
    ає
    -0.06
     heightFor
    -0.06
     House
    -0.06
     af
    -0.06
    öst
    -0.06
     wissen
    -0.06
    POSITIVE LOGITS
     spheres
    0.06
    rollo
    0.06
    krv
    0.06
    (Query
    0.06
    ंश
    0.06
     Himal
    0.06
     CPP
    0.06
     approval
    0.06
     Prop
    0.06
    struct
    0.06
    Act Density 0.047%

    No Known Activations