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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _err
    -0.07
     dn
    -0.07
    槽
    -0.07
    ragment
    -0.07
    _free
    -0.07
    ỡ
    -0.07
     fet
    -0.07
    emplate
    -0.07
    _lift
    -0.06
     kg
    -0.06
    POSITIVE LOGITS
    ASHINGTON
    0.08
    Sorting
    0.07
     også
    0.07
    IBE
    0.07
     Soccer
    0.07
    throat
    0.07
     wirklich
    0.07
     resultados
    0.06
    五金
    0.06
    �
    0.06
    Act Density 0.052%

    No Known Activations