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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    กลาง
    -0.08
     Lub
    -0.07
     build
    -0.06
     benches
    -0.06
     skeptical
    -0.06
    erosis
    -0.06
    -turn
    -0.06
    fuse
    -0.06
     BUILD
    -0.06
     portray
    -0.06
    POSITIVE LOGITS
    μπο
    0.07
     amort
    0.07
     プロ
    0.06
     дозвол
    0.06
    .Thread
    0.06
    CanBeConverted
    0.06
     apartheid
    0.06
    จากการ
    0.06
    (itemView
    0.06
     Forward
    0.06
    Act Density 0.026%

    No Known Activations