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

    Neuronpedia

    INDEX
    Explanations

    say "and"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crispy
    -0.07
     chassis
    -0.07
    .USER
    -0.07
     Hãy
    -0.06
     everyone
    -0.06
    emiz
    -0.06
     aba
    -0.06
     testosterone
    -0.06
    Unchecked
    -0.06
     ulong
    -0.06
    POSITIVE LOGITS
    Issue
    0.06
    '):
    0.06
    (paths
    0.06
     οικο
    0.06
    .(*
    0.06
     stump
    0.06
    เอก
    0.06
    venida
    0.05
    िग
    0.05
    :l
    0.05
    Act Density 0.093%

    No Known Activations