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

    Neuronpedia

    INDEX
    Explanations

    Open, Industry, fairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.53
    destino
    0.52
    Somos
    0.49
    ]):
    0.49
    Cidade
    0.48
     ذلك
    0.46
    الية
    0.46
    cita
    0.46
    ]));
    0.44
    Eso
    0.44
    POSITIVE LOGITS
     օ
    0.55
     enquiry
    0.54
     sculpting
    0.54
     spelling
    0.51
    𝑵
    0.51
    드의
    0.50
     trimming
    0.50
     midwives
    0.49
     orchids
    0.49
     manures
    0.49
    Act Density 0.000%

    No Known Activations