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

    Neuronpedia

    INDEX
    Explanations

    complex, possibly negative sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nonatomic
    -0.07
    .IContainer
    -0.07
    spNet
    -0.06
    crm
    -0.06
    SnackBar
    -0.06
     unfair
    -0.06
     зуст
    -0.06
    olecular
    -0.06
     supermarket
    -0.06
     く
    -0.06
    POSITIVE LOGITS
    aters
    0.07
    loat
    0.07
     Peek
    0.06
    OPS
    0.06
    roy
    0.06
    Ross
    0.06
     Useful
    0.06
     Match
    0.06
     Wise
    0.06
    -goal
    0.06
    Act Density 0.000%

    No Known Activations