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

    Neuronpedia

    INDEX
    Explanations

    null

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fs
    -0.07
    ínu
    -0.07
     probes
    -0.07
     –
    -0.06
    .doc
    -0.06
     protocols
    -0.06
     tinder
    -0.06
     таких
    -0.06
     parasite
    -0.06
     factors
    -0.06
    POSITIVE LOGITS
    locking
    0.06
    .kill
    0.06
    claim
    0.06
     holland
    0.06
    Return
    0.06
    Trade
    0.06
    anganese
    0.06
    Incoming
    0.05
     Chester
    0.05
     OAuth
    0.05
    Act Density 0.062%

    No Known Activations