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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LAP
    -0.07
     recibir
    -0.07
    EC
    -0.07
     CFR
    -0.07
    RM
    -0.07
    icus
    -0.06
    Crop
    -0.06
    ीर
    -0.06
    754
    -0.06
     comedic
    -0.06
    POSITIVE LOGITS
     wanna
    0.09
     We
    0.09
    .
    0.09
     Wanna
    0.09
     Will
    0.08
    To
    0.08
     th
    0.08
     can
    0.08
    We
    0.08
     To
    0.07
    Act Density 0.068%

    No Known Activations