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

    Neuronpedia

    INDEX
    Explanations

    /g

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    raciones
    0.38
    বেশ
    0.37
     Pending
    0.36
    PEND
    0.36
     पेन
    0.36
     nick
    0.36
    Uber
    0.35
    暧
    0.35
     herb
    0.35
    icist
    0.35
    POSITIVE LOGITS
     пала
    0.40
    محمد
    0.40
     GGA
    0.38
     pali
    0.36
    μο
    0.35
     contingency
    0.35
    হা
    0.34
     République
    0.34
     GCC
    0.33
    Chol
    0.33
    Act Density 0.011%

    No Known Activations