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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     depend
    -0.07
    nodiscard
    -0.07
     blueprint
    -0.07
    ça
    -0.07
     scaffold
    -0.06
     conc
    -0.06
    [channel
    -0.06
    如何
    -0.06
     repell
    -0.06
     Accum
    -0.06
    POSITIVE LOGITS
     hodin
    0.06
     sadece
    0.06
    ()<<"
    0.06
    .getChildren
    0.06
    VED
    0.06
    
    0.06
    前の
    0.06
    esh
    0.06
     converting
    0.06
     aes
    0.06
    Act Density 0.000%

    No Known Activations