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

    Neuronpedia

    INDEX
    Explanations

    code snippets / documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RTAL
    -0.07
     bumped
    -0.07
    @\
    -0.06
     Guests
    -0.06
    üçük
    -0.06
    temp
    -0.06
    (cb
    -0.06
     relied
    -0.06
     realized
    -0.06
    Msg
    -0.06
    POSITIVE LOGITS
    idge
    0.08
     πρα
    0.07
    |(
    0.07
     (!(
    0.06
    sen
    0.06
    etection
    0.06
     đề
    0.06
    ز
    0.06
    .fd
    0.06
    ;;;;
    0.06
    Act Density 0.000%

    No Known Activations