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

    Neuronpedia

    INDEX
    Explanations

    need

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /W
    -0.07
    -water
    -0.06
    icerca
    -0.06
    \Active
    -0.06
    Voltage
    -0.06
     dew
    -0.06
    _venta
    -0.06
    .Clone
    -0.06
    ori
    -0.06
     přik
    -0.06
    POSITIVE LOGITS
     needed
    0.08
    _constants
    0.07
    (adapter
    0.07
    99
    0.07
     mathematical
    0.07
     nostra
    0.06
    �
    0.06
     diagram
    0.06
     dragon
    0.06
     Cats
    0.06
    Act Density 0.022%

    No Known Activations