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

    Neuronpedia

    INDEX
    Explanations

    ambassador positions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (async
    -0.08
     Keto
    -0.07
    　 　
    -0.07
     rested
    -0.07
    ]+"
    -0.07
    ุษย
    -0.07
    eşit
    -0.07
    (to
    -0.07
    就会
    -0.06
     которое
    -0.06
    POSITIVE LOGITS
    tone
    0.07
    jf
    0.07
     Clay
    0.06
    YES
    0.06
    localStorage
    0.06
     Cena
    0.06
     Plays
    0.06
    (Handle
    0.06
    =C
    0.05
     QC
    0.05
    Act Density 0.010%

    No Known Activations