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

    Neuronpedia

    INDEX
    Explanations

    Used by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vlan
    -0.07
    。(
    -0.07
    blog
    -0.06
     Nov
    -0.06
    fun
    -0.06
     jailed
    -0.06
    .pref
    -0.06
     virus
    -0.06
     캐
    -0.06
    ч
    -0.06
    POSITIVE LOGITS
    рина
    0.07
     continua
    0.06
     responsibilities
    0.06
     Aging
    0.06
    ）↵
    0.06
     exhausting
    0.06
    ICollection
    0.06
     почти
    0.06
    _bill
    0.06
    _PROM
    0.06
    Act Density 0.051%

    No Known Activations