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

    Neuronpedia

    INDEX
    Explanations

    underground

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plot
    -0.28
     Plot
    -0.28
    ä¿Ħ
    -0.27
     ÑģÑĭ
    -0.26
    ä¹Ķ
    -0.26
    çĶŁçī©åѦ
    -0.25
    Plot
    -0.25
     biological
    -0.24
    æĹĹ
    -0.24
    åī§æĥħ
    -0.24
    POSITIVE LOGITS
    gest
    0.31
    ewise
    0.29
    clair
    0.27
    aways
    0.26
     sixth
    0.26
    æĩĭ
    0.25
    _keyword
    0.25
    æ©«
    0.25
    iked
    0.25
    kad
    0.24
    Act Density 0.014%

    No Known Activations