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

    Neuronpedia

    INDEX
    Explanations

    .write

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     critics
    -0.08
     charging
    -0.07
     BMP
    -0.07
    ceed
    -0.07
    uguay
    -0.07
    cred
    -0.07
    ��
    -0.07
    Clip
    -0.06
    RequestMapping
    -0.06
     citation
    -0.06
    POSITIVE LOGITS
    allel
    0.08
     Wyn
    0.07
     yatırım
    0.06
    .collect
    0.06
     _$
    0.06
    ен
    0.06
     Better
    0.06
     هذه
    0.06
     hardwood
    0.06
     gst
    0.06
    Act Density 0.005%

    No Known Activations