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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     เอ
    -0.07
    人が
    -0.07
    (Resource
    -0.07
    Playback
    -0.07
    portunity
    -0.06
     vak
    -0.06
    .fre
    -0.06
     relación
    -0.06
    "While
    -0.06
    Instruction
    -0.06
    POSITIVE LOGITS
     tableView
    0.07
     pedal
    0.07
    _linear
    0.06
     во
    0.06
    便
    0.06
    _Insert
    0.06
     torch
    0.06
    _good
    0.06
     ads
    0.06
     directory
    0.06
    Act Density 0.160%

    No Known Activations