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

    Neuronpedia

    INDEX
    Explanations

    basis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Shortcut
    -0.08
     SMALL
    -0.07
    gc
    -0.07
    cycl
    -0.07
    마
    -0.07
    _SMALL
    -0.07
    testCase
    -0.07
     GLUT
    -0.06
     Chat
    -0.06
    ㄺ
    -0.06
    POSITIVE LOGITS
    _listen
    0.08
     datas
    0.07
     바랍니다
    0.07
    ᨪ
    0.07
    &s
    0.07
     awakened
    0.07
    	lp
    0.07
     możli
    0.07
     resulting
    0.07
     {_
    0.07
    Act Density 0.009%

    No Known Activations