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

    Neuronpedia

    INDEX
    Explanations

    today

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Startup
    -0.07
     Jul
    -0.06
    Desc
    -0.06
     operated
    -0.06
    Sets
    -0.06
     servi
    -0.06
    issance
    -0.06
     SYSTEM
    -0.06
    eba
    -0.06
    Caller
    -0.06
    POSITIVE LOGITS
     kole
    0.07
    誠
    0.07
    KN
    0.06
     verdade
    0.06
    /id
    0.06
     갑
    0.06
    採
    0.06
    .pack
    0.06
    ='<
    0.06
     '))↵
    0.06
    Act Density 0.067%

    No Known Activations