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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    овали
    -0.06
     worsh
    -0.06
    両
    -0.06
    Enabled
    -0.06
    Church
    -0.06
    Matrix
    -0.06
    HTMLElement
    -0.06
     opin
    -0.06
     plural
    -0.06
     उच
    -0.06
    POSITIVE LOGITS
    -or
    0.06
     stash
    0.06
     outr
    0.06
    _l
    0.06
     wit
    0.06
    _%
    0.06
     marshal
    0.06
     "$
    0.06
     qualify
    0.06
    ë
    0.06
    Act Density 0.089%

    No Known Activations