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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     muted
    -0.07
    olid
    -0.07
     stain
    -0.07
     economically
    -0.06
    fully
    -0.06
     entail
    -0.06
    payload
    -0.06
     carefully
    -0.06
     millions
    -0.06
    Baseline
    -0.06
    POSITIVE LOGITS
     Zahl
    0.08
    .CLASS
    0.07
     στο
    0.07
     CONST
    0.07
     shalt
    0.06
     Entities
    0.06
     таких
    0.06
     koruy
    0.06
     اختصاص
    0.06
     rady
    0.06
    Act Density 0.123%

    No Known Activations