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

    Neuronpedia

    INDEX
    Explanations

    not just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    т
    1.49
     Singapura
    1.46
    യും
    1.30
     UIColor
    1.26
     Jovi
    1.26
    𝘻
    1.23
    ᇁ
    1.23
    VILLE
    1.21
    સર
    1.21
    NavLink
    1.21
    POSITIVE LOGITS
    ни
    1.73
    на
    1.72
    larda
    1.48
    na
    1.44
    sa
    1.44
    nesses
    1.42
    son
    1.39
    ná
    1.34
     be
    1.34
    nél
    1.34
    Act Density 0.062%

    No Known Activations