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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kumar
    -0.06
    aceut
    -0.06
     pockets
    -0.06
     suicide
    -0.06
    unity
    -0.06
    Generic
    -0.06
    .Init
    -0.06
     Stats
    -0.06
    guna
    -0.06
     většinou
    -0.06
    POSITIVE LOGITS
    补
    0.06
    年の
    0.06
    sst
    0.06
    答
    0.06
    亚
    0.06
    셔
    0.06
    atypes
    0.05
    ī
    0.05
     Moms
    0.05
    �
    0.05
    Act Density 0.005%

    No Known Activations