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

    Neuronpedia

    INDEX
    Explanations

    Physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Muse
    -0.08
    elen
    -0.07
    886
    -0.07
    ้าท
    -0.07
     Hudson
    -0.07
    isel
    -0.07
     foto
    -0.07
    існо
    -0.06
     Beach
    -0.06
    _cell
    -0.06
    POSITIVE LOGITS
     valued
    0.06
     которая
    0.06
     �
    0.06
    Sibling
    0.06
    .IT
    0.06
    <(),
    0.06
     val
    0.05
    _MET
    0.05
    _ALIGN
    0.05
     oversight
    0.05
    Act Density 0.060%

    No Known Activations