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

    Neuronpedia

    INDEX
    Explanations

    Alto

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orative
    -0.07
     progen
    -0.07
    ={$
    -0.06
     Lazar
    -0.06
     аж
    -0.06
     опер
    -0.06
    GLenum
    -0.06
     піш
    -0.06
    лад
    -0.06
     Japan
    -0.06
    POSITIVE LOGITS
     Alto
    0.29
     alto
    0.22
    alto
    0.14
    to
    0.07
    adamente
    0.06
     stop
    0.06
    .allowed
    0.06
     Yates
    0.06
     выс
    0.06
     Banco
    0.06
    Act Density 0.001%

    No Known Activations