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

    Neuronpedia

    INDEX
    Explanations

    inform you of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    irió
    0.39
     Então
    0.39
     littered
    0.39
    ähr
    0.38
    arına
    0.38
     mitophagy
    0.37
    ProductName
    0.37
     feedback
    0.37
     relatable
    0.37
     ProductName
    0.36
    POSITIVE LOGITS
     _$
    0.37
     plunge
    0.37
    꿋
    0.36
    xsl
    0.35
     strife
    0.35
     apres
    0.34
     jl
    0.34
    卅
    0.33
    ukung
    0.33
    erzo
    0.33
    Act Density 0.001%

    No Known Activations