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

    Neuronpedia

    INDEX
    Explanations

    code/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istine
    -0.29
    inc
    -0.27
     //{↵
    -0.26
    ãģ¹
    -0.26
    ĵį
    -0.26
    MethodImpl
    -0.25
    idelity
    -0.25
     unfavorable
    -0.24
     nurs
    -0.24
     incor
    -0.24
    POSITIVE LOGITS
    orra
    0.29
    inar
    0.29
    xDE
    0.28
    nder
    0.27
     arrays
    0.26
     amounts
    0.26
    ña
    0.24
     hy
    0.24
    æķ°ç»Ħ
    0.24
    ãģ¤ãģĭ
    0.24
    Act Density 0.040%

    No Known Activations