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

    Neuronpedia

    INDEX
    Explanations

    water

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ice
    -0.07
    ica
    -0.07
    DA
    -0.07
    Agents
    -0.07
     disproportionate
    -0.07
    iquid
    -0.06
    '^
    -0.06
     enviado
    -0.06
     vocational
    -0.06
    ICC
    -0.06
    POSITIVE LOGITS
     değiş
    0.07
     STYLE
    0.06
    --
    0.06
     terror
    0.06
    pred
    0.06
    法院
    0.05
    vla
    0.05
     tar
    0.05
    <translation
    0.05
     meds
    0.05
    Act Density 0.017%

    No Known Activations