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

    Neuronpedia

    INDEX
    Explanations

    parentheses and brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ¥
    -0.07
    Shape
    -0.07
     clip
    -0.06
    Persona
    -0.06
    DOUBLE
    -0.06
    ~~
    -0.06
     monde
    -0.06
     PBS
    -0.06
     predators
    -0.06
    dbus
    -0.06
    POSITIVE LOGITS
    alace
    0.06
     kel
    0.06
     tritur
    0.06
     ist
    0.06
    (">
    0.06
     decisions
    0.06
     UNITED
    0.06
    acades
    0.06
     banking
    0.06
     retrospect
    0.06
    Act Density 0.005%

    No Known Activations