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

    Neuronpedia

    INDEX
    Explanations

    —

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dgv
    -0.06
     progressing
    -0.06
    dap
    -0.06
     Belgium
    -0.06
     링
    -0.06
    .strings
    -0.06
     Denver
    -0.06
     tí
    -0.06
    Most
    -0.06
    队
    -0.06
    POSITIVE LOGITS
     Positions
    0.08
     вывод
    0.07
    FACT
    0.07
    ška
    0.06
    @Configuration
    0.06
     Mouse
    0.06
     Savior
    0.06
    سال
    0.06
    Wo
    0.06
    _supported
    0.06
    Act Density 0.003%

    No Known Activations