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

    Neuronpedia

    INDEX
    Explanations

    Live performances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _gradient
    -0.09
     gradient
    -0.09
    负责人
    -0.08
    _grad
    -0.08
    担当
    -0.08
     masculine
    -0.08
     gradients
    -0.08
    owners
    -0.08
    ograd
    -0.08
    oczes
    -0.08
    POSITIVE LOGITS
     recordings
    0.16
     filmed
    0.15
    Recorded
    0.14
    Recording
    0.14
    録
    0.13
     Recorded
    0.13
     recording
    0.13
     Recording
    0.12
    录像
    0.12
     footage
    0.12
    Act Density 0.044%

    No Known Activations