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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    孕
    -0.08
     قادر
    -0.08
     galaxy
    -0.07
     tossed
    -0.07
    _hidden
    -0.07
    .orm
    -0.07
     dragon
    -0.07
     budget
    -0.07
     omn
    -0.07
    Ñ
    -0.06
    POSITIVE LOGITS
    ])
    0.08
    )){
    0.07
    uala
    0.07
     Па
    0.07
    _Msp
    0.07
    провод
    0.07
    前期
    0.06
    testimonial
    0.06
    Increases
    0.06
    .Low
    0.06
    Act Density 0.003%

    No Known Activations