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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝘌
    -0.07
     Flames
    -0.07
    :ss
    -0.07
    مخاطر
    -0.06
     lords
    -0.06
    融合
    -0.06
     findAll
    -0.06
    	model
    -0.06
     reopened
    -0.06
     criticisms
    -0.06
    POSITIVE LOGITS
    memory
    0.09
    يان
    0.07
     Battery
    0.07
    Margin
    0.06
    Depth
    0.06
    Time
    0.06
     giorno
    0.06
    iPad
    0.06
    Partition
    0.06
     Microsystems
    0.06
    Act Density 0.026%

    No Known Activations