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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istring
    -0.07
     trận
    -0.07
     vec
    -0.06
    alling
    -0.06
    ička
    -0.06
     Movement
    -0.06
    AWN
    -0.06
    ieurs
    -0.06
    -sw
    -0.06
     Ψ
    -0.06
    POSITIVE LOGITS
     희
    0.07
    (()=>
    0.06
    eparator
    0.06
    ภายใน
    0.06
     crushed
    0.06
    หลาย
    0.06
    建议
    0.06
     taxonomy
    0.06
     stdClass
    0.06
     vener
    0.06
    Act Density 0.035%

    No Known Activations