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

    Neuronpedia

    INDEX
    Explanations

    Social media engagement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hade
    -0.07
    boru
    -0.07
     Conflict
    -0.06
    .dataSource
    -0.06
    فع
    -0.06
    odings
    -0.06
     operation
    -0.06
     arreglo
    -0.06
     unimagin
    -0.06
    ому
    -0.06
    POSITIVE LOGITS
    <label
    0.06
     Creating
    0.06
    ------------------------------
    0.06
     champs
    0.06
     vfs
    0.06
    érica
    0.06
     Глав
    0.06
     ACPI
    0.06
     categorical
    0.06
    лага
    0.05
    Act Density 0.036%

    No Known Activations