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

    Neuronpedia

    INDEX
    Explanations

    trained in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rave
    -0.09
     Burnett
    -0.09
    mania
    -0.09
     ortaya
    -0.09
    ably
    -0.08
    allo
    -0.08
    lse
    -0.08
    aire
    -0.08
    ands
    -0.08
     Handy
    -0.08
    POSITIVE LOGITS
     how
    0.16
    å¦Ĥä½ķ
    0.14
    how
    0.13
     να
    0.10
     Äijá»ĥ
    0.10
     cómo
    0.10
    nesc
    0.10
    spot
    0.10
     hvordan
    0.09
     matters
    0.09
    Act Density 0.059%

    No Known Activations