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

    Neuronpedia

    INDEX
    Explanations

    blue face

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     genres
    0.52
    يح
    0.49
     vases
    0.48
     wineries
    0.48
     flags
    0.47
    𝗘
    0.46
     velocities
    0.46
    𝙠
    0.46
     orders
    0.45
    ক
    0.44
    POSITIVE LOGITS
     тщательно
    0.45
     Santo
    0.41
     Erschein
    0.41
    大切
    0.40
    脉
    0.40
    가는
    0.39
    面上
    0.39
                        
    0.39
    留在
    0.39
     lão
    0.39
    Act Density 0.000%

    No Known Activations