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

    Neuronpedia

    INDEX
    Explanations

    specific keywords and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     revolution
    0.36
    Computation
    0.35
     computation
    0.34
     obtuse
    0.33
     veil
    0.33
     ob
    0.33
     intricately
    0.32
     Computation
    0.31
     rhombus
    0.31
     tiles
    0.31
    POSITIVE LOGITS
    渴
    0.38
    écl
    0.38
    0.37
    Olivia
    0.36
     இந்நிலையில்
    0.35
    𒆳
    0.34
     danos
    0.33
    (\|\
    0.33
     باسکٹ
    0.33
    yrıca
    0.33
    Act Density 0.000%

    No Known Activations