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

    Neuronpedia

    INDEX
    Explanations

    java

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pedido
    -0.07
    ,path
    -0.07
     entrar
    -0.06
    _listing
    -0.06
    ával
    -0.06
    ablytyped
    -0.06
    developer
    -0.06
    _strike
    -0.06
    дается
    -0.06
    _USER
    -0.06
    POSITIVE LOGITS
    hum
    0.07
    Aut
    0.06
     energ
    0.06
     neut
    0.06
    creativecommons
    0.06
    /met
    0.06
    -प
    0.06
     CASE
    0.06
     Beam
    0.06
     beam
    0.06
    Act Density 0.009%

    No Known Activations