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

    Neuronpedia

    INDEX
    Explanations

    Non-English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     escalated
    -0.06
    .section
    -0.06
    }
↵
↵
↵
↵
    -0.06
    ?>'
    -0.06
    otte
    -0.06
     camping
    -0.05
    rchive
    -0.05
     customer
    -0.05
     aus
    -0.05
     Naw
    -0.05
    POSITIVE LOGITS
     Riy
    0.07
     받아
    0.07
    (non
    0.06
    □
    0.06
    [float
    0.06
     BX
    0.06
     axs
    0.06
     Brill
    0.06
    (reader
    0.06
     초기
    0.06
    Act Density 0.005%

    No Known Activations