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

    Neuronpedia

    INDEX
    Explanations

    emotionally adjusted robot explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     실패
    0.44
    𝗺
    0.42
     こんにちは
    0.41
     ejaculation
    0.41
    satunya
    0.41
    𝚖
    0.41
     വിജ
    0.39
     కూ
    0.39
    𝚐
    0.39
     απ
    0.38
    POSITIVE LOGITS
     posso
    0.41
     Boyd
    0.39
     Bianco
    0.38
     puedo
    0.37
     Baker
    0.37
    Dew
    0.36
     podemos
    0.36
    %>%
    0.35
    Zach
    0.34
    alal
    0.34
    Act Density 0.000%

    No Known Activations