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

    Neuronpedia

    INDEX
    Explanations

    IP address and network configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    0.43
    ెర
    0.39
    بد
    0.39
    trimethyl
    0.38
    бль
    0.37
     troubled
    0.37
    ậm
    0.37
    eryl
    0.37
     ذکر
    0.37
    erval
    0.36
    POSITIVE LOGITS
    IP
    0.53
     ip
    0.53
     Kip
    0.53
    SIP
    0.53
     ips
    0.51
    otesi
    0.51
     आईपी
    0.50
     kip
    0.50
    cip
    0.50
    आईपी
    0.49
    Act Density 0.029%

    No Known Activations