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

    Neuronpedia

    INDEX
    Explanations

    Expressing desires/expectations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pet
    -0.08
     Aspir
    -0.08
     laad
    -0.07
     asbestos
    -0.07
     repeat
    -0.07
     ulang
    -0.07
     immobilier
    -0.07
     Lobby
    -0.07
     Southwestern
    -0.07
     effet
    -0.07
    POSITIVE LOGITS
     unchanged
    0.09
    、更
    0.09
    .sg
    0.08
     occasionally
    0.08
     unidentified
    0.08
    ẫn
    0.08
     còn
    0.08
    PLAY
    0.08
     તેનો
    0.07
     intact
    0.07
    Act Density 0.241%

    No Known Activations