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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _choice
    -0.07
    žila
    -0.07
    ři
    -0.06
    Fit
    -0.06
     nouveau
    -0.06
    žil
    -0.06
    >Edit
    -0.06
     Eve
    -0.06
     arrives
    -0.06
     elective
    -0.06
    POSITIVE LOGITS
    قم
    0.07
     навч
    0.06
     про
    0.06
     �
    0.06
     Fem
    0.06
     SKU
    0.06
    �
    0.06
    ुक
    0.06
     наказ
    0.06
    (rows
    0.06
    Act Density 0.004%

    No Known Activations