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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    shelf
    -0.07
     Trevor
    -0.07
     deployed
    -0.07
    הפכו
    -0.07
    [var
    -0.07
    所有人
    -0.07
     anymore
    -0.07
    yer
    -0.07
     Glenn
    -0.07
    战友
    -0.07
    POSITIVE LOGITS
     Hash
    0.08
    .setVerticalGroup
    0.07
     Express
    0.07
     Usuario
    0.07
    membership
    0.07
     Taj
    0.06
    hci
    0.06
     MSS
    0.06
    ITLE
    0.06
    羽毛
    0.06
    Act Density 0.207%

    No Known Activations