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

    Neuronpedia

    INDEX
    Explanations

    Plans, actions, responsibilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thường
    -0.07
    mtree
    -0.06
     olds
    -0.06
     sel
    -0.06
    اني
    -0.06
     Cars
    -0.06
     artisans
    -0.06
     Rs
    -0.06
    _intensity
    -0.05
     résult
    -0.05
    POSITIVE LOGITS
    marginTop
    0.07
     조선
    0.07
     revived
    0.07
    рет
    0.06
    ButtonClick
    0.06
    orry
    0.06
    opor
    0.06
    &action
    0.06
     traceback
    0.06
    PYTHON
    0.06
    Act Density 0.052%

    No Known Activations