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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ermög
    -0.07
     apopt
    -0.07
    红色
    -0.07
    不仅可以
    -0.06
     migli
    -0.06
     either
    -0.06
     serious
    -0.06
     hữu
    -0.06
     massive
    -0.06
    孤
    -0.06
    POSITIVE LOGITS
    ,address
    0.07
    =''
    0.07
    ,_
    0.07
    _TYPEDEF
    0.07
    ˁ
    0.07
    Ⓢ
    0.07
     רבה
    0.07
    ParticleSystem
    0.07
     permissible
    0.07
    _buff
    0.06
    Act Density 0.154%

    No Known Activations