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

    Neuronpedia

    INDEX
    Explanations

    With

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     who
    -0.07
     how
    -0.07
     also
    -0.07
    quirrel
    -0.07
    NR
    -0.07
    GER
    -0.07
     intermitt
    -0.07
     Mrs
    -0.06
     burnt
    -0.06
     rather
    -0.06
    POSITIVE LOGITS
     With
    0.14
    With
    0.13
    "With
    0.10
     with
    0.08
    .With
    0.07
     WITH
    0.06
    with
    0.06
    —with
    0.06
     vessel
    0.06
     spanish
    0.06
    Act Density 0.027%

    No Known Activations