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

    Neuronpedia

    INDEX
    Explanations

    scientific comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -have
    -0.06
    ,Integer
    -0.06
     Transformers
    -0.06
     téc
    -0.06
     içine
    -0.06
     masa
    -0.06
    CrLf
    -0.06
    icked
    -0.06
    etermined
    -0.06
     enclosed
    -0.06
    POSITIVE LOGITS
    ージ
    0.08
    CAF
    0.07
     kernel
    0.07
    ibern
    0.07
    ><
    0.07
     marg
    0.06
     آ
    0.06
     youthful
    0.06
     spear
    0.06
    чів
    0.06
    Act Density 0.106%

    No Known Activations