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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     콘
    -0.07
     Ninth
    -0.07
    arrays
    -0.07
     breed
    -0.07
     nob
    -0.06
     topology
    -0.06
    telephone
    -0.06
    ampoline
    -0.06
    cycle
    -0.06
    .Itoa
    -0.06
    POSITIVE LOGITS
    的手
    0.08
     Cory
    0.07
    0.06
     한
    0.06
    εις
    0.06
    elier
    0.06
     は
    0.06
    grave
    0.06
     HK
    0.06
    -dev
    0.06
    Act Density 0.000%

    No Known Activations