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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    560
    -0.07
    /*.
    -0.07
    SKIP
    -0.07
     compiling
    -0.07
    ぼ
    -0.06
    نسا
    -0.06
     Lambert
    -0.06
     tongue
    -0.06
     homem
    -0.06
    melon
    -0.06
    POSITIVE LOGITS
    ользоват
    0.07
    械
    0.06
     restrain
    0.06
    ManagedObject
    0.06
    .IsDBNull
    0.06
     gemeins
    0.06
    ，从
    0.06
     Anadolu
    0.06
    _Release
    0.06
     चर
    0.06
    Act Density 0.031%

    No Known Activations