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

    Neuronpedia

    INDEX
    Explanations

    descriptions of orientation or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    direction and orientation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Successfully
    -0.40
     successfully
    -0.37
     createState
    -0.35
     BitmapFactory
    -0.35
     gathered
    -0.34
     OSError
    -0.34
    ccoli
    -0.34
     reunió
    -0.34
    UserDTO
    -0.34
     createStore
    -0.34
    POSITIVE LOGITS
     Facing
    0.72
    Facing
    0.72
     towards
    0.71
     facing
    0.71
     toward
    0.69
     Towards
    0.68
     Toward
    0.68
    Towards
    0.68
    towards
    0.65
    Toward
    0.64
    Act Density 0.022%

    No Known Activations