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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alls
    -0.07
     alex
    -0.07
    gone
    -0.07
     contraseña
    -0.06
    _sent
    -0.06
     buddy
    -0.06
    Sequence
    -0.06
    alling
    -0.06
    entialAction
    -0.06
     mj
    -0.06
    POSITIVE LOGITS
    -"
    0.06
     नद
    0.06
     лак
    0.06
     Phạm
    0.06
    ENDOR
    0.06
     چگونه
    0.06
     تولید
    0.06
    ="#">
    0.06
    jections
    0.06
     atmospheric
    0.06
    Act Density 0.036%

    No Known Activations