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

    Neuronpedia

    INDEX
    Explanations

    knowledge base

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Chair
    0.38
    ること
    0.38
    bmc
    0.38
     바람
    0.37
     منص
    0.37
     અન્ય
    0.37
    Mas
    0.37
     جایی
    0.37
    砖
    0.37
     Ir
    0.36
    POSITIVE LOGITS
    loop
    0.42
     sensores
    0.41
    🔋
    0.39
     polarizer
    0.38
     vouch
    0.37
    ✗
    0.36
     detects
    0.34
    camera
    0.34
     corrobor
    0.34
    鉗
    0.34
    Act Density 0.000%

    No Known Activations