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

    Neuronpedia

    INDEX
    Explanations

    Beetles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _iters
    -0.07
     Journey
    -0.07
     Conway
    -0.07
    ERT
    -0.07
    Vo
    -0.07
    yas
    -0.07
     RTE
    -0.06
     concurrently
    -0.06
    ddit
    -0.06
     Jo
    -0.06
    POSITIVE LOGITS
    局长
    0.07
     rp
    0.07
    �
    0.07
     adhesive
    0.07
     bols
    0.07
     untouched
    0.06
    汪
    0.06
    ?.
    0.06
    (policy
    0.06
     Sey
    0.06
    Act Density 0.003%

    No Known Activations