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

    Neuronpedia

    INDEX
    Explanations

    in for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RSVP
    -0.07
     _↵
    -0.07
     sont
    -0.06
    께
    -0.06
    ADIO
    -0.06
     Clause
    -0.06
    _PUSH
    -0.06
     проч
    -0.06
     док
    -0.06
     restitution
    -0.06
    POSITIVE LOGITS
     TouchableOpacity
    0.07
     рань
    0.06
    Plug
    0.06
    Climate
    0.06
    arris
    0.06
    fuel
    0.06
    _inventory
    0.06
    êu
    0.06
    agers
    0.06
    isser
    0.06
    Act Density 0.040%

    No Known Activations