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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     startDate
    -0.07
    OUNDS
    -0.07
     LB
    -0.07
     banking
    -0.07
     raging
    -0.06
     knights
    -0.06
     haste
    -0.06
     librarian
    -0.06
     Unsafe
    -0.06
    .RIGHT
    -0.06
    POSITIVE LOGITS
    मक
    0.06
     Cater
    0.06
    crm
    0.06
    [q
    0.06
     aktif
    0.06
    othy
    0.06
    .for
    0.06
    ________
    0.06
     第三
    0.06
    msp
    0.05
    Act Density 0.004%

    No Known Activations