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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    보험
    -0.06
    starttime
    -0.06
     Todo
    -0.06
    _layers
    -0.06
     typedef
    -0.06
    _todo
    -0.06
    .styleable
    -0.06
    Normalize
    -0.06
    Adding
    -0.06
    Remark
    -0.06
    POSITIVE LOGITS
     Mayıs
    0.07
     curled
    0.07
    伦
    0.07
    lyn
    0.07
     initialState
    0.06
    HEL
    0.06
    Wr
    0.06
    bre
    0.06
     OPER
    0.06
     meziná
    0.06
    Act Density 0.010%

    No Known Activations