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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sneak
    -0.07
    �
    -0.07
    _dic
    -0.07
    eye
    -0.06
    collapsed
    -0.06
     vlan
    -0.06
     più
    -0.06
     Luxembourg
    -0.06
     схем
    -0.06
    ($"{
    -0.06
    POSITIVE LOGITS
    xb
    0.07
    achel
    0.07
    .playlist
    0.06
    porate
    0.06
     piger
    0.06
     حس
    0.06
    areth
    0.06
    anggan
    0.06
     deviation
    0.06
     Herbert
    0.06
    Act Density 0.100%

    No Known Activations