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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lui
    -0.07
     Perfect
    -0.07
     cabinet
    -0.07
    olo
    -0.07
     provád
    -0.06
    estimated
    -0.06
     яку
    -0.06
     medications
    -0.06
     sensitive
    -0.06
     FFT
    -0.06
    POSITIVE LOGITS
    :key
    0.07
    \base
    0.06
    /bus
    0.06
     initialState
    0.06
     womb
    0.06
     hd
    0.06
    _STEP
    0.06
    \E
    0.06
    .xmlbeans
    0.06
    710
    0.06
    Act Density 0.049%

    No Known Activations