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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (keys
    -0.07
     Conce
    -0.07
    .ce
    -0.06
     hierarchical
    -0.06
     메
    -0.06
    romium
    -0.06
     Kü
    -0.06
     populist
    -0.06
     vào
    -0.06
    CASCADE
    -0.06
    POSITIVE LOGITS
     ''↵
    0.06
     %[
    0.06
     videot
    0.06
     genders
    0.06
     initiatives
    0.06
    ruta
    0.06
    질
    0.06
    под
    0.06
    €€€€
    0.06
     ])↵
    0.06
    Act Density 0.049%

    No Known Activations