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

    Neuronpedia

    INDEX
    Explanations

    giving advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hope
    -0.07
    _type
    -0.07
    STER
    -0.06
    message
    -0.06
    periences
    -0.06
    .lastName
    -0.06
     Jr
    -0.06
    ız
    -0.06
    TypeId
    -0.06
    BBBB
    -0.06
    POSITIVE LOGITS
     προ
    0.07
    asad
    0.06
     Colombia
    0.06
     LaTeX
    0.06
     Shots
    0.06
    ợ
    0.06
     Với
    0.06
     вообще
    0.06
    _PACK
    0.06
     सज
    0.06
    Act Density 0.027%

    No Known Activations