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

    Neuronpedia

    INDEX
    Explanations

    teaching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     koup
    -0.07
    ocre
    -0.07
    HIP
    -0.07
     nord
    -0.07
     Ire
    -0.07
    XF
    -0.07
     IMP
    -0.07
    erland
    -0.07
     corre
    -0.07
    +C
    -0.06
    POSITIVE LOGITS
     teaching
    0.08
    .draw
    0.06
    _URI
    0.06
    	mask
    0.06
    Video
    0.06
    detach
    0.06
    _UNDER
    0.06
    attach
    0.06
     Teaching
    0.06
     skips
    0.05
    Act Density 0.016%

    No Known Activations