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

    Neuronpedia

    INDEX
    Explanations

    plotting code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.08
     Treat
    -0.07
    ّر
    -0.06
    рак
    -0.06
    224
    -0.06
    (da
    -0.06
    êm
    -0.06
    IP
    -0.06
    latest
    -0.06
    Command
    -0.06
    POSITIVE LOGITS
     chac
    0.07
     niños
    0.07
     फर
    0.06
     dm
    0.06
     Majority
    0.06
     rg
    0.06
     tslint
    0.06
    bellion
    0.06
    	elseif
    0.06
    .=
    0.06
    Act Density 0.004%

    No Known Activations