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

    Neuronpedia

    INDEX
    Explanations

    hotel reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    альная
    -0.07
    .showMessage
    -0.07
    etary
    -0.06
    альних
    -0.06
    pollo
    -0.06
     maneuvers
    -0.06
     echt
    -0.06
     yans
    -0.06
    -fly
    -0.05
     List
    -0.05
    POSITIVE LOGITS
     ApplicationController
    0.07
     PCB
    0.07
     Trouble
    0.07
    .";↵
    0.07
    '));
↵
    0.07
    igidBody
    0.07
    Sounds
    0.07
    Cube
    0.07
    ");
↵
    0.06
     -*-↵↵
    0.06
    Act Density 0.048%

    No Known Activations