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

    Neuronpedia

    INDEX
    Explanations

    trajectory

    np_max-act · gemini-2.0-flash

    The neuron primarily detects occurrences of the word “trajectory” (and its plural form “trajectories”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     wider
    -0.06
    νε
    -0.06
     removal
    -0.06
     oldest
    -0.06
    FilterWhere
    -0.06
     praise
    -0.06
     Servers
    -0.06
    YPES
    -0.06
    Spaces
    -0.05
     shl
    -0.05
    POSITIVE LOGITS
     trajectories
    0.12
     trajectory
    0.10
    _traj
    0.08
    trajectory
    0.08
     Journey
    0.07
    foil
    0.07
     Mango
    0.07
    και
    0.07
     IsActive
    0.07
     放
    0.07
    Act Density 0.005%

    No Known Activations