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

    Neuronpedia

    INDEX
    Explanations

    hash map lookup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dictate
    0.44
     Dick
    0.43
     Duct
    0.42
     duct
    0.42
     dik
    0.41
    Dik
    0.41
     dictated
    0.40
    Dick
    0.39
    dik
    0.38
     dictates
    0.38
    POSITIVE LOGITS
     hash
    1.88
     Hash
    1.84
    Hash
    1.84
    hash
    1.59
    HashMap
    1.53
     hashes
    1.51
     hasht
    1.45
     Hasht
    1.45
     HashMap
    1.42
    HASH
    1.42
    Act Density 0.036%

    No Known Activations