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

    Neuronpedia

    INDEX
    Explanations

    problems and solutions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ib
    -0.07
     clothes
    -0.07
     ropes
    -0.06
     ourselves
    -0.06
    Bro
    -0.06
    🍍
    -0.06
    OTS
    -0.06
    胳膊
    -0.06
     nâ
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    aliases
    0.08
    imer
    0.07
    вод
    0.07
    ож
    0.07
    븜
    0.07
     TIMER
    0.07
    מין
    0.07
    chrift
    0.07
    (dictionary
    0.07
     gg
    0.07
    Act Density 0.034%

    No Known Activations