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

    Neuronpedia

    INDEX
    Explanations

    TV show reviews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iste
    -0.07
    ISING
    -0.07
    UED
    -0.07
    ید
    -0.07
    比
    -0.07
    IAL
    -0.06
    ]+
    -0.06
     ，
    -0.06
    ORN
    -0.06
    tp
    -0.06
    POSITIVE LOGITS
     }}>↵
    0.06
     Tiffany
    0.06
    .Dao
    0.06
     CSR
    0.06
     flam
    0.06
     �
    0.06
     пос
    0.06
     ubiquitous
    0.06
     Suff
    0.06
    -we
    0.06
    Act Density 0.006%

    No Known Activations