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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SOFT
    -0.07
     rewriting
    -0.07
    нимать
    -0.07
     freaking
    -0.07
    _texture
    -0.07
     sono
    -0.07
    omo
    -0.07
     происходит
    -0.07
     tree
    -0.06
    .client
    -0.06
    POSITIVE LOGITS
     품
    0.06
     وزار
    0.06
     BUFFER
    0.06
    UITextField
    0.06
    raised
    0.06
     scrap
    0.06
    forc
    0.06
     mj
    0.06
    cap
    0.05
    .pass
    0.05
    Act Density 0.001%

    No Known Activations