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

    Neuronpedia

    INDEX
    Explanations

    Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     refinery
    -0.08
    "))
    -0.07
    _sock
    -0.07
     رفتار
    -0.06
    oker
    -0.06
     soğ
    -0.06
    _np
    -0.06
    _NEG
    -0.06
    RTL
    -0.06
    wife
    -0.06
    POSITIVE LOGITS
    لسل
    0.06
     Apartments
    0.06
    命令
    0.06
    664
    0.06
     slaughtered
    0.06
     prise
    0.05
     rencont
    0.05
    ив
    0.05
     surve
    0.05
     clauses
    0.05
    Act Density 0.048%

    No Known Activations