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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oxide
    -0.07
     Kids
    -0.07
     pile
    -0.06
     temples
    -0.06
    _fold
    -0.06
     HDF
    -0.06
    astics
    -0.06
     imap
    -0.06
    uite
    -0.06
    .pick
    -0.06
    POSITIVE LOGITS
    entionPolicy
    0.07
     reported
    0.07
    جاد
    0.06
    stations
    0.06
     exquisite
    0.06
    .transport
    0.06
     *
    0.06
    stride
    0.06
    ैग
    0.06
    _infos
    0.06
    Act Density 0.000%

    No Known Activations