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

    Neuronpedia

    INDEX
    Explanations

    Version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ihtiy
    -0.06
    elled
    -0.06
    dds
    -0.06
    ASCII
    -0.06
    대의
    -0.06
    _nv
    -0.06
    '],
    -0.06
    .positions
    -0.06
    ازه
    -0.06
    (interface
    -0.06
    POSITIVE LOGITS
     assemble
    0.07
     earning
    0.07
     Di
    0.07
     hiring
    0.06
     regenerate
    0.06
    リ
    0.06
    (beta
    0.06
     preparing
    0.06
     critically
    0.06
     Collaboration
    0.06
    Act Density 0.001%

    No Known Activations