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

    Neuronpedia

    INDEX
    Explanations

    'm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nod
    -0.06
     plug
    -0.06
     Epstein
    -0.06
     protection
    -0.06
    -dollar
    -0.05
    Projection
    -0.05
     uplat
    -0.05
    ctime
    -0.05
    漫画
    -0.05
     руч
    -0.05
    POSITIVE LOGITS
    ="">
↵
    0.07
     Lydia
    0.07
    .Cryptography
    0.07
     mashed
    0.07
    .Test
    0.06
    orgeous
    0.06
    thern
    0.06
    prm
    0.06
    DMA
    0.06
     ALLOW
    0.06
    Act Density 0.038%

    No Known Activations