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

    Neuronpedia

    INDEX
    Explanations

    concentration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     behaviour
    -0.07
     vd
    -0.07
     chars
    -0.07
    .credit
    -0.07
    Python
    -0.06
     modification
    -0.06
     книж
    -0.06
     навіть
    -0.06
     віднов
    -0.06
    items
    -0.06
    POSITIVE LOGITS
    γκα
    0.07
    ，就
    0.07
     cumpl
    0.07
     cena
    0.06
     concentrations
    0.06
    Signature
    0.06
     chick
    0.06
     monitor
    0.06
     concentration
    0.06
    ствия
    0.06
    Act Density 0.005%

    No Known Activations